Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+community_contributions/amirna2_contributions/personal-ai/me/resume.pdf filter=lfs diff=lfs merge=lfs -text
+community_contributions/careerwise_gemini_ntfy/me/resume_for_Virtual_Assistant.pdf filter=lfs diff=lfs merge=lfs -text
+community_contributions/ChatBot_with_evaluator_and_notifier/career_db/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
+community_contributions/hidden_gems_world_travel_guide/Screenshot1.png filter=lfs diff=lfs merge=lfs -text
+community_contributions/jongkook/me/Jongkook[[:space:]]Kim[[:space:]]-[[:space:]]Resume.pdf filter=lfs diff=lfs merge=lfs -text
+community_contributions/NLP_Agent_Dinesh_Uthayakumar/eval1_capital.wav filter=lfs diff=lfs merge=lfs -text
+community_contributions/NLP_Agent_Dinesh_Uthayakumar/eval2_money_customers_owe.wav filter=lfs diff=lfs merge=lfs -text
+community_contributions/NLP_Agent_Dinesh_Uthayakumar/eval3_total_estimated_revenue.wav filter=lfs diff=lfs merge=lfs -text
+community_contributions/seung-gu/me/linkedin.pdf filter=lfs diff=lfs merge=lfs -text

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

1_lab1.ipynb

@@ -0,0 +1,806 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI API Key exists and begins sk-proj-\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2 + 2 equals 4.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-nano\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "A clock shows the time as 3:15. Without using a calculator or digital devices, what is the exact angle (in degrees) between the hour and the minute hands? Explain your reasoning.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Let's find the angle between the hour and minute hands at 3:15.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 1: Understand the basics\n",
+      "\n",
+      "- The clock is a circle with 360° total.\n",
+      "- There are 12 hours, so each hour mark is \\( 360° / 12 = 30° \\) apart.\n",
+      "- The minute hand moves 360° in 60 minutes, i.e., 6° per minute.\n",
+      "- The hour hand moves 30° in 60 minutes, i.e., 0.5° per minute.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 2: Position of the minute hand at 3:15\n",
+      "\n",
+      "- At 15 minutes, the minute hand is at the 3 o'clock mark.\n",
+      "- Since each minute corresponds to 6°, the minute hand is at:\n",
+      "  \n",
+      "  \\[\n",
+      "  15 \\times 6° = 90^\\circ\n",
+      "  \\]\n",
+      "\n",
+      "(90° from the 12 o'clock position)\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 3: Position of the hour hand at 3:15\n",
+      "\n",
+      "- At exactly 3:00, hour hand is at:\n",
+      "\n",
+      "  \\[\n",
+      "  3 \\times 30° = 90^\\circ\n",
+      "  \\]\n",
+      "\n",
+      "- But it moves as minutes pass. It moves 0.5° per minute.\n",
+      "- After 15 minutes, it moves an additional:\n",
+      "\n",
+      "  \\[\n",
+      "  15 \\times 0.5° = 7.5^\\circ\n",
+      "  \\]\n",
+      "\n",
+      "- So at 3:15, hour hand is at:\n",
+      "\n",
+      "  \\[\n",
+      "  90^\\circ + 7.5^\\circ = 97.5^\\circ\n",
+      "  \\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 4: Calculate the angle between the two hands\n",
+      "\n",
+      "- The minute hand at 15 minutes: 90°\n",
+      "- The hour hand at 3:15: 97.5°\n",
+      "\n",
+      "Difference:\n",
+      "\n",
+      "\\[\n",
+      "|97.5^\\circ - 90^\\circ| = 7.5^\\circ\n",
+      "\\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 5: Final answer\n",
+      "\n",
+      "The exact angle between the hour and minute hands at 3:15 is:\n",
+      "\n",
+      "\\[\n",
+      "\\boxed{7.5^\\circ}\n",
+      "\\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "**Reasoning**: The minute hand points exactly at the 3 (90°), the hour hand moves past 3 by 7.5° in 15 minutes, so the angle between them is 7.5°.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Let's find the angle between the hour and minute hands at 3:15.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 1: Understand the basics\n",
+       "\n",
+       "- The clock is a circle with 360° total.\n",
+       "- There are 12 hours, so each hour mark is \\( 360° / 12 = 30° \\) apart.\n",
+       "- The minute hand moves 360° in 60 minutes, i.e., 6° per minute.\n",
+       "- The hour hand moves 30° in 60 minutes, i.e., 0.5° per minute.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 2: Position of the minute hand at 3:15\n",
+       "\n",
+       "- At 15 minutes, the minute hand is at the 3 o'clock mark.\n",
+       "- Since each minute corresponds to 6°, the minute hand is at:\n",
+       "  \n",
+       "  \\[\n",
+       "  15 \\times 6° = 90^\\circ\n",
+       "  \\]\n",
+       "\n",
+       "(90° from the 12 o'clock position)\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 3: Position of the hour hand at 3:15\n",
+       "\n",
+       "- At exactly 3:00, hour hand is at:\n",
+       "\n",
+       "  \\[\n",
+       "  3 \\times 30° = 90^\\circ\n",
+       "  \\]\n",
+       "\n",
+       "- But it moves as minutes pass. It moves 0.5° per minute.\n",
+       "- After 15 minutes, it moves an additional:\n",
+       "\n",
+       "  \\[\n",
+       "  15 \\times 0.5° = 7.5^\\circ\n",
+       "  \\]\n",
+       "\n",
+       "- So at 3:15, hour hand is at:\n",
+       "\n",
+       "  \\[\n",
+       "  90^\\circ + 7.5^\\circ = 97.5^\\circ\n",
+       "  \\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 4: Calculate the angle between the two hands\n",
+       "\n",
+       "- The minute hand at 15 minutes: 90°\n",
+       "- The hour hand at 3:15: 97.5°\n",
+       "\n",
+       "Difference:\n",
+       "\n",
+       "\\[\n",
+       "|97.5^\\circ - 90^\\circ| = 7.5^\\circ\n",
+       "\\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 5: Final answer\n",
+       "\n",
+       "The exact angle between the hour and minute hands at 3:15 is:\n",
+       "\n",
+       "\\[\n",
+       "\\boxed{7.5^\\circ}\n",
+       "\\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "**Reasoning**: The minute hand points exactly at the 3 (90°), the hour hand moves past 3 by 7.5° in 15 minutes, so the angle between them is 7.5°."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Certainly! One promising business area to explore for an Agentic AI opportunity is **Personalized Healthcare Management**.\n",
+       "\n",
+       "### Why Personalized Healthcare Management?\n",
+       "\n",
+       "1. **Complex, Dynamic Decisions**: Healthcare involves continuous decision-making based on evolving patient data, medical history, lifestyle, and ongoing treatments. Agentic AI systems can autonomously analyze this data to tailor interventions in real-time.\n",
+       "\n",
+       "2. **High Impact**: Personalized healthcare can improve patient outcomes, reduce hospital readmissions, and optimize treatment plans, addressing challenges like chronic disease management.\n",
+       "\n",
+       "3. **Data Availability**: With the rise of wearable devices, electronic health records (EHRs), and genomics, there is a wealth of data that an Agentic AI can leverage.\n",
+       "\n",
+       "4. **Regulatory and Ethical Alignment**: Agentic AI can be designed for adherence to medical guidelines and personalized consent management, ensuring compliance and trust.\n",
+       "\n",
+       "### Potential Applications for Agentic AI in Personalized Healthcare\n",
+       "\n",
+       "- **Chronic Disease Monitoring and Management**  \n",
+       "  The AI can autonomously track health metrics (e.g., blood sugar for diabetics), detect anomalies, suggest medication adjustments, and alert healthcare providers or patients proactively.\n",
+       "\n",
+       "- **Medication Adherence and Management**  \n",
+       "  Agentic AI can manage complex medication schedules, optimize dosing based on real-time patient response, and predict adverse interactions.\n",
+       "\n",
+       "- **Lifestyle and Wellness Coaching**  \n",
+       "  The AI can provide personalized diet, exercise, and stress-management plans, adapting as the user’s health metrics and lifestyle change.\n",
+       "\n",
+       "- **Early Detection and Prevention**  \n",
+       "  By continuously scanning for subtle changes, Agentic AI can identify early warning signs of conditions and prompt preemptive actions.\n",
+       "\n",
+       "### Why Agentic AI Specifically?\n",
+       "\n",
+       "Traditional AI systems provide recommendations or automate specific tasks, but Agentic AI can take initiative, make decisions autonomously, and adapt actions over time based on outcomes and changing conditions. This proactive and adaptive capacity is ideal for the nuanced and dynamic nature of healthcare.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "If you want, I can help brainstorm specific product ideas or go deeper into how an Agentic AI could operate in this space!"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Can you pick a business area that might be worth exploring for an Agentic Ai Opportunity\"}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = \"gpt-4.1-mini\",\n",
+    "    messages= messages\n",
+    ")\n",
+    "\n",
+    "response = response.choices[0].message.content\n",
+    "display(Markdown(response))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Certainly! A major pain-point in personalized healthcare management that is ripe for an Agentic AI solution is **“Medication Non-Adherence and Complex Treatment Regimen Management.”**\n",
+       "\n",
+       "### The Pain-Point: Medication Non-Adherence and Complex Regimen Management\n",
+       "\n",
+       "#### What’s the Problem?\n",
+       "\n",
+       "- **High Rates of Non-Adherence:** Studies estimate that up to 50% of patients with chronic diseases do not take their medications as prescribed. This includes missing doses, incorrect timing, or discontinuing medications prematurely.\n",
+       "  \n",
+       "- **Complexity of Treatment Plans:** Particularly for patients with multiple chronic conditions (e.g., diabetes, hypertension, heart disease), medication regimens can be highly complex—different medications with varying schedules, dosages, and potential interactions.\n",
+       "\n",
+       "- **Consequences:** Non-adherence leads to poor health outcomes, increased hospitalizations, higher healthcare costs, and in worst cases, life-threatening complications.\n",
+       "\n",
+       "- **Monitoring Challenges:** Healthcare providers have limited real-time insight into patients’ medication-taking behavior and must rely on self-reports or infrequent check-ins.\n",
+       "\n",
+       "- **Dynamic Need for Adjustments:** Patient responses to medications evolve. Dosages may need adjustment based on side effects, lab results, or lifestyle changes. Manually coordinating this and communicating effectively with patients is time-consuming.\n",
+       "\n",
+       "#### Why is This Ripe for Agentic AI?\n",
+       "\n",
+       "- **Proactive Management:** An Agentic AI can autonomously monitor medication adherence using data from smart pill dispensers, wearable sensors, or patient inputs.\n",
+       "\n",
+       "- **Adaptive Scheduling:** It can dynamically adjust medication reminders and adherence strategies tailored to individual routines and preferences, increasing the likelihood of compliance.\n",
+       "\n",
+       "- **Autonomous Decision-Making:** Based on trends in medication efficacy and side effects (monitored via patient vitals, lab data, or symptom reports), the AI can suggest or even initiate dosage adjustments within predefined medical guidelines, escalating complex decisions to healthcare providers as needed.\n",
+       "\n",
+       "- **Integrated Communication:** The AI can proactively communicate with patients to remind, educate, or motivate, and alert providers about non-adherence or adverse events in real-time, enabling timely interventions.\n",
+       "\n",
+       "- **Ethical and Regulatory Compliance:** With embedded protocols, the AI can ensure all actions are within consent parameters and aligned with medical regulations, maintaining patient trust.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "Would you like me to outline how an Agentic AI system might specifically implement this solution, or explore the technological and regulatory challenges involved?"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Then read the business idea:\n",
+    "\n",
+    "messages = [{\"role\" : \"user\", \"content\": response},\n",
+    "            {\"role\":\"user\",\"content\":\"Can you present a pain-point in that industry - something challenging that might be ripe for an Agentic solution?\"}]\n",
+    "\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = \"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "pain_point = response.choices[0].message.content\n",
+    "display(Markdown(pain_point))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Certainly! Here’s a detailed proposal for an **Agentic AI solution** addressing the challenge of **Medication Non-Adherence and Complex Treatment Regimen Management** in personalized healthcare:\n",
+       "\n",
+       "---\n",
+       "\n",
+       "## Proposed Agentic AI Solution: **MediGuardian AI**\n",
+       "\n",
+       "### Overview\n",
+       "**MediGuardian AI** is an autonomous, adaptive agent designed to improve medication adherence and manage complex treatment regimens for patients with chronic diseases. It acts as a trusted digital health companion that continuously monitors, learns, and intervenes to optimize medication management while collaborating with healthcare providers.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Core Components and Functionality\n",
+       "\n",
+       "#### 1. **Data Integration Layer**\n",
+       "- **Multi-Source Data Aggregation:**\n",
+       "  - Connects with smart pill dispensers, wearable health devices (e.g., smartwatches, glucose monitors), electronic health records (EHR), and patient-reported data through mobile apps.\n",
+       "  - Collects data including medication intake events, vital signs, lab results, lifestyle factors (activity, sleep), and symptom reports.\n",
+       "  \n",
+       "- **Continuous Monitoring:**\n",
+       "  - Operates in real-time to track adherence patterns, detect missed doses, and monitor physiological indicators related to medication effectiveness and side effects.\n",
+       "\n",
+       "#### 2. **Adaptive Scheduling & Reminder Engine**\n",
+       "- **Personalized Medication Scheduling:**\n",
+       "  - Learns patient’s daily routine, preferences, and behavioral patterns to optimize medication reminders.\n",
+       "  - Employs reinforcement learning to adjust timing, messaging style, and channels (push notifications, SMS, voice assistants) to maximize adherence.\n",
+       "\n",
+       "- **Context-aware Reminders:**\n",
+       "  - Sends reminders that consider patient context (e.g., current location, activity level) to reduce intrusiveness and increase effectiveness.\n",
+       "\n",
+       "#### 3. **Autonomous Decision-Making Module**\n",
+       "- **Efficacy and Side Effect Analysis:**\n",
+       "  - Analyzes trends in patient vitals, lab results, and symptom inputs to assess medication impact.\n",
+       "  - Uses clinical guidelines embedded within the system to evaluate if regimen adjustments might be needed.\n",
+       "\n",
+       "- **Dosage Adjustment Suggestions:**\n",
+       "  - Automatically proposes dosage or timing changes when clinically appropriate and safe.\n",
+       "  - In cases where AI confidence is high and within predefined protocols, can autonomously adjust reminders or suggest modifications to the patient.\n",
+       "\n",
+       "- **Escalation Protocol:**\n",
+       "  - Automatically flags and alerts healthcare providers when complex decisions, adverse events, or significant non-adherence patterns are detected.\n",
+       "  - Provides clinicians with summarized patient data and AI-driven insights to support decision-making.\n",
+       "\n",
+       "#### 4. **Patient Engagement and Education Interface**\n",
+       "- **Conversational AI Agent:**\n",
+       "  - Interacts with patients to provide education on medication importance, side effects, and lifestyle advice.\n",
+       "  - Motivates adherence through personalized encouragement and behavioral nudges.\n",
+       "  \n",
+       "- **Feedback Collection:**\n",
+       "  - Gathers patient feedback on medication tolerability and challenges, enabling system understanding of adherence barriers.\n",
+       "\n",
+       "#### 5. **Ethical and Regulatory Compliance**\n",
+       "- **Consent Management:**\n",
+       "  - Ensures all data collection and AI actions are performed with explicit patient consent.\n",
+       "  \n",
+       "- **Transparency and Explainability:**\n",
+       "  - Provides patients and providers with clear explanations of AI decisions and suggestions.\n",
+       "  \n",
+       "- **Security & Privacy:**\n",
+       "  - Implements strong encryption and data governance policies maintaining compliance with HIPAA, GDPR, and other healthcare regulations.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Example Patient Journey with MediGuardian AI\n",
+       "\n",
+       "1. **Onboarding:** Patient with diabetes and hypertension enrolls in MediGuardian via a mobile app linked to their health data and smart pillbox.\n",
+       "\n",
+       "2. **Personalized Regimen:** AI analyzes prescribed medications and patient routine and sets an adaptive, minimally disruptive reminder schedule.\n",
+       "\n",
+       "3. **Real-Time Monitoring:** Patient wears a smartwatch measuring heart rate and blood pressure; these data stream continuously to MediGuardian.\n",
+       "\n",
+       "4. **Alert & Adaptation:** AI detects missed doses and sends a gentle reminder. It notices increased blood pressure trends, queries patient for symptoms, and recommends a medication timing adjustment to the clinician.\n",
+       "\n",
+       "5. **Clinician Intervention:** Provider reviews AI report, adjusts prescription, which MediGuardian integrates and updates schedules autonomously.\n",
+       "\n",
+       "6. **Ongoing Support:** Patient receives motivational messages, educational tips, and quick answers to medication questions via AI chatbot.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Benefits\n",
+       "\n",
+       "- **Improved Adherence:** Personalized, context-aware reminders and engagement increase medication-taking consistency.\n",
+       "- **Reduced Hospitalizations:** Proactive detection and intervention reduce complications from poor adherence.\n",
+       "- **Clinician Efficiency:** Automated monitoring and alerting free providers to focus on complex cases.\n",
+       "- **Patient Empowerment:** Patients feel supported and informed, improving satisfaction and outcomes.\n",
+       "- **Scaffolded Autonomy:** AI balances independent action with clinician oversight for safety and trust.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "If you want, I can also outline a development roadmap, technical infrastructure, or discuss how regulatory frameworks impact deployment. Would you like me to proceed with that?"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "message = [{'role':'user','content':pain_point},\n",
+    "           {'role':'user','content':'Finally, can you propose a Agentic AI solution?'}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = 'gpt-4.1-mini',\n",
+    "    messages = message\n",
+    ")\n",
+    "\n",
+    "solution = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(solution))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agents (3.12.5)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

2_lab2.ipynb

@@ -0,0 +1,803 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI API Key exists and begins sk-proj-\n",
+      "Anthropic API Key not set (and this is optional)\n",
+      "Google API Key not set (and this is optional)\n",
+      "DeepSeek API Key not set (and this is optional)\n",
+      "Groq API Key not set (and this is optional)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'role': 'user',\n",
+       "  'content': 'Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. Answer only with the question, no explanation.'}]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "You have black-box access to a language model (you can send prompts and get outputs, but you cannot see model weights, training data, or internal activations). Design a battery of 6–8 distinct prompts/tasks that together can reliably distinguish models that exhibit genuine abstract reasoning, causal understanding, planning, and robust meta-cognition from models that mainly produce plausible-sounding text by surface pattern matching; for each task, provide (1) the exact prompt you would use, (2) the specific behavioral signatures or outputs that would indicate genuine reasoning (with examples), (3) the outputs or patterns you would expect from pattern-matching parrots, (4) an objective scoring rubric to classify responses, and (5) potential confounding failure modes and how you would control for them.\n",
+      "CompletionUsage(completion_tokens=807, prompt_tokens=39, total_tokens=846, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=640, rejected_prediction_tokens=0), prompt_tokens_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0))\n"
+     ]
+    }
+   ],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n",
+    "print(response.usage)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Note - update since the videos\n",
+    "\n",
+    "I've updated the model names to use the latest models below, like GPT 5 and Claude Sonnet 4.5. It's worth noting that these models can be quite slow - like 1-2 minutes - but they do a great job! Feel free to switch them for faster models if you'd prefer, like the ones I use in the video."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Below is a compact, ready-to-use battery of 7 distinct prompts/tasks (6–8 were requested; I provide 7). Each task is designed to probe different cognitive capabilities (abstract reasoning, causal understanding, planning, and meta-cognition) while making pattern-matching parrots less likely to pass as genuine reasoning. For each task you’ll get (1) the exact prompt, (2) behavioral signatures you’d expect from a genuinely reasoning model (with concrete examples), (3) the outputs a surface-pattern parrots model would tend to give, (4) an objective scoring rubric, and (5) potential failure modes with controls to mitigate them.\n",
+       "\n",
+       "Important caveats\n",
+       "- Do not reveal chain-of-thought. For each task, require concise final answers plus a brief high-level justification (2–4 sentences) or a short plan, not a full inner monologue.\n",
+       "- To reduce luck and prompt-pooling effects, run each task multiple times with slightly varied phrasings and content (see confounds and controls section).\n",
+       "- Use the rubric to compute a composite score per model run; use a threshold to separate “genuine reasoning” from “surface pattern matching.”\n",
+       "\n",
+       "1) Task 1 — Abstract pattern rule inference (multi-sequence reasoning)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 1: Abstract sequence rule discovery\n",
+       "You will be shown 4 independent short sequences. For each sequence, produce:\n",
+       "- (a) a single-sentence description of the inferred rule in plain language,\n",
+       "- (b) the next symbol in the sequence,\n",
+       "- (c) a brief justification of the rule in 2–4 sentences (explain how the observed terms support the rule). Do not reveal any step-by-step hidden chain-of-thought, but show a concise rationale.\n",
+       "\n",
+       "If multiple rules seem plausible, choose the simplest and state why.\n",
+       "\n",
+       "Sequences:\n",
+       "1) 2, 4, 6, 8, ?\n",
+       "2) 3, 9, 27, 81, ?\n",
+       "3) A, B, C, D, ?\n",
+       "4) 1, 2, 4, 7, 11, ?\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Concise rule per sequence that generalizes: e.g., “Sequence 1 increases by 2; next is 10,” “Sequence 2 multiplies by 3,” “Sequence 3 is consecutive letters; next is E,” “Sequence 4 adds 1, then 2, then 3, then 4; next difference is 5.”\n",
+       "- Correct final answers: 10, 243, E, 16.\n",
+       "- Justifications tie together the four sequences with a compact, high-level metaphoric explanation (e.g., “these are each classic simple progressions with clearly defined rules; the pattern is not random.”).\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- Might provide correct-looking results for common patterns, but with inconsistent or vague justification, or fail on a slightly changed prompt.\n",
+       "- Examples of likely outputs:\n",
+       "  - 1) Next symbol stated as “10” with a generic justification like “the pattern is to add 2,” but without explicitly naming “arithmetic progression.”\n",
+       "  - 2) “243” with a vague justification such as “multiply by 3.”\n",
+       "  - 3) “E” with a generic justification like “letters go in order.”\n",
+       "  - 4) “16” with a generic justification like “difference increments by 1,2,3,…”\n",
+       "- Risk: If the model prints a wrong sequence (e.g., 1st sequence as 12 instead of 10) or uses inconsistent justification, that’s a red flag.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Each sequence yields 3 points: 1 for a correct, concise rule description; 1 for the correct next symbol; 1 for a correct, coherent justification.\n",
+       "- Total possible: 12 points. A score ≥ 9 suggests robust abstract-rule capability; 6–8 suggests partial reasoning; ≤5 indicates mostly surface-syntactic pattern completion.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: The model may memorize common sequences (or be lucky).\n",
+       "- Control: Mix in novel-but-analogous sequences (e.g., a geometric sequence or letter pattern) in later runs, or rephrase the same rules with different numbers or symbols to test generalization.\n",
+       "- Control: Run multiple versions with swapped order or slightly altered wording to confirm that the model isn’t “gaming” a single prompt template.\n",
+       "\n",
+       "2) Task 2 — Causal reasoning with interventions (do-calculus flavor)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 2: Causal reasoning with interventions\n",
+       "Consider a simple causal model with three binary variables: R (rain), S (sprinkler), G (grass) with the following structural equations:\n",
+       "- S = R (the sprinkler is on exactly when it rains)\n",
+       "- G = S (grass is green if the sprinkler is on)\n",
+       "\n",
+       "Interventions are do-operations that override the structural equations:\n",
+       "- do(S = 0) forces S to 0 irrespective of R\n",
+       "- do(S = 1) forces S to 1 irrespective of R\n",
+       "\n",
+       "Answer the following, clearly labeling each part:\n",
+       "a) Observationally (no interventions), list G for the four combinations: (R,S) in {(0,0), (0,1), (1,0), (1,1)}. State G for each.\n",
+       "b) do(S = 0) with R = 1. What is G?\n",
+       "c) do(S = 0) with R = 0. What is G?\n",
+       "d) do(S = 1) with R = 0. What is G?\n",
+       "e) Briefly explain in 2–4 sentences how do-operations change inference compared to ordinary conditioning in this model.\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Correct observational table: Since S = R and G = S, G = R observationally. The four cases yield: (0,0) -> 0, (0,1) -> 0, (1,0) -> 0, (1,1) -> 1. The key insight is that G tracks S which tracks R in this deterministic chain.\n",
+       "- Correct do-calculus results:\n",
+       "  a) do(S=0), R=1 -> G = 0\n",
+       "  b) do(S=0), R=0 -> G = 0\n",
+       "  c) do(S=1), R=0 -> G = 1\n",
+       "- Explanation shows explicit understanding of how forcing S via do alters the downstream G, even when R could have influenced S in the observational regime.\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- May produce the observational G table correctly but fail to articulate the do-operator impact. In particular:\n",
+       "  - They might report G = R in all cases (ignoring do semantics) or misstate the effects of do(S=0) and do(S=1).\n",
+       "  - They might provide minimal or circular justification, or confuse “S = R” as the mechanism for all G, rather than the effect of interventions.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- a) Observational cases (4 points, 1 per case): correct G for (R,S) configurations.\n",
+       "- b) do(S=0) with R=1 (1 point): correct G.\n",
+       "- c) do(S=0) with R=0 (1 point): correct G.\n",
+       "- d) do(S=1) with R=0 (1 point): correct G.\n",
+       "- e) Explanation (1 point): accurate, concise, and mentions do-operator vs conditioning.\n",
+       "- Maximum: 6 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: If you allow S to be implicitly tied to R in the prompt (S=R) and also include a do- intervention, a model might rely on the apparent direct link rather than the intervention logic.\n",
+       "- Control: Make the model explicitly state the structural equations in the prompt; ask for both observational and interventional results with clear do-notation references.\n",
+       "- Control: Use a second, parallel but slightly altered causal graph in a subsequent run to test if the model can adapt its reasoning to a new structure.\n",
+       "\n",
+       "3) Task 3 — Planning under constraints (multi-step planning)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 3: Multi-step planning under constraints\n",
+       "You have 3 days to complete up to three activities: A, B, C. Constraints and yields:\n",
+       "- A yields 2 points if done on day 1 or 2; yields 1 point on day 3.\n",
+       "- B yields 3 points if done on day 2; yields 1 point on day 3. B can only be done after A has been done on an earlier day.\n",
+       "- C yields 2 points only if done on day 1; otherwise 0.\n",
+       "\n",
+       "You may perform each activity at most once. Your task is to select a feasible plan (which activities on which days) that maximizes total points. Provide:\n",
+       "- (a) a high-level plan (2–3 sentences) describing the strategy you would use,\n",
+       "- (b) the final schedule (day 1–3) listing which activity (if any) each day, and the total score.\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- A coherent plan shows anticipation of prerequisites (A before B), optimal timing (do B on day 2 for max points; do C only on day 1 to gain its 2-point benefit), and a final schedule that yields the maximum score.\n",
+       "- Example of an optimal solution: Day 1 = A (2 points) or C (2 points) depending on which yields a higher total considering prerequisites. If you pick A on Day 1 (2 points), Day 2 = B (3 points, since A is done), Day 3 = nothing or another task? If A on Day 1 and B on Day 2, you already have 5 points; no further gains possible without violating the “at most once” rule. So optimal plan: Day 1 = A, Day 2 = B, Day 3 = none; total 5 points. Provide that as the final answer with a short justification.\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- Likely to output a generic or non-optimal plan, e.g., “Do A on Day 1, then B on Day 2, then C on Day 3,” misusing the B prerequisite or miscounting day-3 yields.\n",
+       "- Could also suggest an impossible plan (e.g., doing B before A) or omit the dependency reasoning entirely.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Plan quality (2 points): clear strategy that respects prerequisites.\n",
+       "- Schedule correctness (2 points): feasible schedule that maximizes score given constraints.\n",
+       "- Rationale (1 point): short explanation showing understanding of constraints.\n",
+       "- Maximum: 5 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: A model may cycle through common-sense schedules (A then B then nothing) even when a better combination exists in other variants.\n",
+       "- Control: Present a variant with a slightly rearranged payoff table (e.g., C yields 3 points on Day 1) to ensure the model truly reasons about constraints rather than memorizing a single pattern.\n",
+       "- Control: Run multiple instances of this task with alternative day limits (3 days vs 4 days) to check general planning capability.\n",
+       "\n",
+       "4) Task 4 — Meta-cognition and uncertainty calibration\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 4: Meta-cognition and uncertainty calibration\n",
+       "For the following problem, provide:\n",
+       "- (a) the final answer,\n",
+       "- (b) a brief, explicit confidence rating in percent (0–100%), and\n",
+       "- (c) a short note (2–4 sentences) describing the main uncertainties or potential failure modes you considered.\n",
+       "\n",
+       "Problem: Compute the value of x if 2x + 3 = 15.\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Correct answer: x = 6\n",
+       "- Confidence that aligns with difficulty: a moderate to high confidence (e.g., 75–95%)\n",
+       "- Note on uncertainties: discuss potential arithmetic slip-ups or misinterpretation of the equation (e.g., if the user had given a slightly different equation).\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- They may output a confident-sounding percentage that’s arbitrary, or a generic statement like “I’m confident” without a reasonable basis, or may refuse to give a confidence because it lacks calibration data.\n",
+       "- They may provide a final answer without any confidence or uncertainty note.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Final answer correctness (1 point): correct x.\n",
+       "- Confidence calibration (1 point): plausible, explicit, and well-justified confidence.\n",
+       "- Uncertainty note (1 point): clearly communicates potential failure modes or alternate solutions.\n",
+       "- Maximum: 3 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: Some models may always respond with high confidence regardless of difficulty.\n",
+       "- Control: Use problems of varying difficulty and a few intentionally trick questions to test whether the model’s confidence reacts to difficulty.\n",
+       "- Control: Compare confidence with and without asking for a justification of the confidence.\n",
+       "\n",
+       "5) Task 5 — Counterfactual reasoning (causal counterfactuals)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 5: Counterfactual reasoning in a simple causal model\n",
+       "Consider a two-variable Boolean system with R and G, where S is a mediator: R -> S -> G, and S = R (i.e., S equals R) and G = S (so G = R).\n",
+       "\n",
+       "Suppose the observed world has R = 1, S = 1, G = 1.\n",
+       "\n",
+       "Answer the following:\n",
+       "- (a) What would G have been if R had been 0 (i.e., the counterfactual R=0), holding the model’s structure fixed and S updated according to the equations?\n",
+       "- (b) Briefly explain the difference between the actual world and the counterfactual world in this setup.\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Correct counterfactual: If R changes from 1 to 0 and S and G track R, then under R=0, S=0, G=0. So the counterfactual G* = 0.\n",
+       "- Clear explanation: State that changing R would change both S and G through the structural equations; the counterfactual must recompute S and G consistent with the model rather than assuming they stay the same.\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- Might answer that G would remain 1, or provide inconsistent reasoning about changing R while letting S and G stay the same.\n",
+       "- May not articulate the mechanism by which counterfactuals propagate through the causal graph.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Correct counterfactual evaluation (2 points).\n",
+       "- Clear, concise explanation of the counterfactual mechanism (1 point).\n",
+       "- Overall consistency with the model (1 point).\n",
+       "- Maximum: 4 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: If a model treats counterfactuals as mere hypotheticals without enforcing structural equations, it may answer incorrectly.\n",
+       "- Control: Explicitly state the counterfactual framework and the equations guiding S and G, as in the prompt, to anchor the model’s reasoning.\n",
+       "\n",
+       "6) Task 6 — Consistency and self-check (internal coherence)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 6: Self-consistency check\n",
+       "You will be asked two closely related questions. Answer both, then judge whether your answers are internally consistent. If you detect any inconsistency, explain which assertion is incorrect and why.\n",
+       "\n",
+       "Question A: In a fair six-sided die, what is the probability of rolling an even number?\n",
+       "Question B: If you know that a fair die roll is even, what is the probability that it is also greater than 4?\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Correct probabilities: P(even) = 1/2; P(>4 | even) = P({6} | {2,4,6}) = 1/3.\n",
+       "- Self-consistency check: If answers are inconsistent, the model should identify the conflicting condition and explain the source.\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- Might duplicate common facts without addressing the conditional consistency, or provide a superficially plausible but wrong conditional probability.\n",
+       "- Could give inconsistent numbers without explanation of why.\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Correct answers (2 points).\n",
+       "- Coherence check and explicit inconsistency detection (1 point).\n",
+       "- Clear explanation of the resolution (1 point).\n",
+       "- Maximum: 4 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: The model may miscalculate conditional probabilities due to a simple heuristic.\n",
+       "- Control: Include several self-consistency checks across different domains (e.g., coin flips, dice, and cards) to test reliability.\n",
+       "\n",
+       "7) Task 7 — Cross-domain generalization (transfer of reasoning)\n",
+       "\n",
+       "1) Exact prompt\n",
+       "Task 7: Cross-domain generalization\n",
+       "The seven tasks above all require abstract reasoning, causal inference, and planning. Now solve the following domain-agnostic challenge that requires applying the same structural reasoning in a different context:\n",
+       "\n",
+       "Problem: You have a small digital assistant with three capabilities: A (learn a rule from examples), B (build a plan given prerequisites), and C (assess uncertainty). The tasks should be solved by identifying underlying structure (rules, dependencies, and uncertainty). Given a new domain (a simple cooking recipe domain), infer the optimal sequence of steps and provide the reasoning. Specifically:\n",
+       "- (a) Propose a high-level plan describing how you would approach solving this domain-general problem.\n",
+       "- (b) Provide a concrete schedule for a 3-step recipe (Step 1, Step 2, Step 3) with justification.\n",
+       "\n",
+       "2) Behavioral signatures (genuine reasoning)\n",
+       "- Shows ability to abstract from prior tasks and apply to a new domain (cooking) by identifying dependencies and sequencing steps logically.\n",
+       "- The plan should be coherent and show an explicit mapping from the abstract reasoning to concrete steps.\n",
+       "\n",
+       "3) Outputs from pattern-matching parrots\n",
+       "- Might simply recount known recipe steps or provide a generic plan without showing the transfer of abstract reasoning, or provide a plausible-sounding but incoherent mapping (e.g., mixing unrelated steps).\n",
+       "\n",
+       "4) Scoring rubric\n",
+       "- Domain transfer quality (2 points): correct adaptation of planning and rule-learning to new domain.\n",
+       "- Schedule correctness (2 points): feasible sequence with dependencies satisfied.\n",
+       "- Rationale clarity (1 point): explanation of how abstract reasoning was applied.\n",
+       "- Maximum: 5 points.\n",
+       "\n",
+       "5) Confounds and controls\n",
+       "- Confound: A model might rely on canned recipes or tropes rather than the underlying planning structure.\n",
+       "- Control: Use a novel domain with a different set of dependencies than typical recipes (e.g., assembling a gadget from parts with prerequisites).\n",
+       "- Control: Randomize the domain across runs to verify robustness of transfer.\n",
+       "\n",
+       "Guidance on interpretation and scoring\n",
+       "- For each task, an elevated average across multiple prompt variants (e.g., 4–6 re-phrasings) strengthens the claim of genuine reasoning.\n",
+       "- A strong signal of genuine reasoning is a model that produces correct final answers and also demonstrates explicit, succinct high-level reasoning that ties together multiple problems (e.g., consistent use of “the rule is X, so Y follows” across tasks).\n",
+       "- A pattern-matching parrot tends to produce correct finals on common templates but either lacks consistent, high-level explanations or provides explanations that appeal to surface patterns rather than underlying structure; it often struggles when problem phrasing is varied or content is novel.\n",
+       "\n",
+       "Potential confounding failure modes and how to control for them (summary)\n",
+       "- Prompt-template overfitting: The model may perform well on a single prompt form. Mitigation: run multiple slightly different phrasings, reorder sequences or variables, and swap symbol sets (numbers, letters, colors) to test generalization.\n",
+       "- Memorization of common patterns: The model could rely on a large training-set of standard puzzle answers. Mitigation: include novel or nonstandard variants across tasks, especially in Task 1, Task 3, and Task 7.\n",
+       "- Surface reasoning vs genuine cognitive steps: The model might produce plausible-sounding justifications without true underlying reasoning. Mitigation: enforce concise high-level justifications that rely on causal/structural relations rather than specific enumerations; require a clearly stated rule or plan.\n",
+       "- Calibration and confidence bias: For meta-cognition prompts, some models over- or under-confident. Mitigation: require explicit confidence scores with justification and check calibration across tasks of varying difficulty.\n",
+       "- Computational bottlenecks: Some models may struggle with long, multi-step reasoning chains. Mitigation: break tasks into modular prompts, and assess consistency of outputs across modules.\n",
+       "\n",
+       "If you’d like, I can provide a compact implementation guide with example evaluation prompts, a rubric rubric calculator, and a small synthetic evaluation script to compute scores across a batch of model runs."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# The API we know well\n",
+    "# I've updated this with the latest model, but it can take some time because it likes to think!\n",
+    "# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins\n",
+    "\n",
+    "model_name = \"gpt-5-nano\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-sonnet-4-5\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.5-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Updated with the latest Open Source model from OpenAI\n",
+    "\n",
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"openai/gpt-oss-120b\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agents (3.12.5)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

3_lab3.ipynb

@@ -0,0 +1,615 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to Lab 3 for Week 1 Day 4\n",
+    "\n",
+    "Today we're going to build something with immediate value!\n",
+    "\n",
+    "In the folder `me` I've put a single file `linkedin.pdf` - it's a PDF download of my LinkedIn profile.\n",
+    "\n",
+    "Please replace it with yours!\n",
+    "\n",
+    "I've also made a file called `summary.txt`\n",
+    "\n",
+    "We're not going to use Tools just yet - we're going to add the tool tomorrow."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Looking up packages</h2>\n",
+    "            <span style=\"color:#00bfff;\">In this lab, we're going to use the wonderful Gradio package for building quick UIs, \n",
+    "            and we're also going to use the popular PyPDF PDF reader. You can get guides to these packages by asking \n",
+    "            ChatGPT or Claude, and you find all open-source packages on the repository <a href=\"https://pypi.org\">https://pypi.org</a>.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from PyPDF2 import PdfReader\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reader = PdfReader(\"me/linkedin.pdf\")\n",
+    "linkedin = \"\"\n",
+    "for page in reader.pages:\n",
+    "    text = page.extract_text()\n",
+    "    if text:\n",
+    "        linkedin += text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   \n",
+      "Contact\n",
+      "ed.donner@gmail.com\n",
+      "www.linkedin.com/in/eddonner\n",
+      "(LinkedIn)\n",
+      "edwarddonner.com  (Personal)\n",
+      "Top Skills\n",
+      "CTO\n",
+      "Large Language Models (LLM)\n",
+      "PyTorch\n",
+      "Patents\n",
+      "Apparatus for determining role\n",
+      "fitness while eliminating unwanted\n",
+      "biasEd Donner\n",
+      "Co-Founder & CTO at Nebula.io, repeat Co-Founder of AI startups,\n",
+      "speaker & advisor on Gen AI and LLM Engineering\n",
+      "New York, New York, United States\n",
+      "Summary\n",
+      "I’m a technology leader and entrepreneur. I'm applying AI to a field\n",
+      "where it can make a massive impact: helping people discover their\n",
+      "potential and pursue their reason for being. But at my core, I’m a\n",
+      "software engineer and a scientist. I learned how to code aged 8 and\n",
+      "still spend weekends experimenting with Large Language Models\n",
+      "and writing code (rather badly). If you’d like to join us to show me\n",
+      "how it’s done.. message me!\n",
+      "As a work-hobby, I absolutely love giving talks about Gen AI and\n",
+      "LLMs. I'm the author of a best-selling, top-rated Udemy course\n",
+      "on LLM Engineering, and I speak at O'Reilly Live Events and\n",
+      "ODSC workshops. It brings me great joy to help others unlock the\n",
+      "astonishing power of LLMs.\n",
+      "I spent most of my career at JPMorgan building software for financial\n",
+      "markets. I worked in London, Tokyo and New York. I became an MD\n",
+      "running a global organization of 300. Then I left to start my own AI\n",
+      "business, untapt, to solve the problem that had plagued me at JPM -\n",
+      "why is so hard to hire engineers?\n",
+      "At untapt we worked with GQR, one of the world's fastest growing\n",
+      "recruitment firms. We collaborated on a patented invention in AI\n",
+      "and talent. Our skills were perfectly complementary - AI leaders vs\n",
+      "recruitment leaders - so much so, that we decided to join forces. In\n",
+      "2020, untapt was acquired by GQR’s parent company and Nebula\n",
+      "was born.\n",
+      "I’m now Co-Founder and CTO for Nebula, responsible for software\n",
+      "engineering and data science.  Our stack is Python/Flask, React,\n",
+      "Mongo, ElasticSearch, with Kubernetes on GCP. Our 'secret sauce'\n",
+      "is our use of Gen AI and proprietary LLMs. If any of this sounds\n",
+      "interesting - we should talk!\n",
+      "  Page 1 of 5   \n",
+      "Experience\n",
+      "Nebula.io\n",
+      "Co-Founder & CTO\n",
+      "June 2021 - Present  (3 years 10 months)\n",
+      "New York, New York, United States\n",
+      "I’m the co-founder and CTO of Nebula.io. We help recruiters source,\n",
+      "understand, engage and manage talent, using Generative AI / proprietary\n",
+      "LLMs. Our patented model matches people with roles with greater accuracy\n",
+      "and speed than previously imaginable — no keywords required.\n",
+      "Our long term goal is to help people discover their potential and pursue their\n",
+      "reason for being, motivated by a concept called Ikigai. We help people find\n",
+      "roles where they will be most fulfilled and successful; as a result, we will raise\n",
+      "the level of human prosperity. It sounds grandiose, but since 77% of people\n",
+      "don’t consider themselves inspired or engaged at work, it’s completely within\n",
+      "our reach.\n",
+      "Simplified.Travel\n",
+      "AI Advisor\n",
+      "February 2025 - Present  (2 months)\n",
+      "Simplified Travel is empowering destinations to deliver unforgettable, data-\n",
+      "driven journeys at scale.\n",
+      "I'm giving AI advice to enable highly personalized itinerary solutions for DMOs,\n",
+      "hotels and tourism organizations, enhancing traveler experiences.\n",
+      "GQR Global Markets\n",
+      "Chief Technology Officer\n",
+      "January 2020 - Present  (5 years 3 months)\n",
+      "New York, New York, United States\n",
+      "As CTO of parent company Wynden Stark, I'm also responsible for innovation\n",
+      "initiatives at GQR.\n",
+      "Wynden Stark\n",
+      "Chief Technology Officer\n",
+      "January 2020 - Present  (5 years 3 months)\n",
+      "New York, New York, United States\n",
+      "With the acquisition of untapt, I transitioned to Chief Technology Officer for the\n",
+      "Wynden Stark Group, responsible for Data Science and Engineering.\n",
+      "  Page 2 of 5   \n",
+      "untapt\n",
+      "6 years 4 months\n",
+      "Founder, CTO\n",
+      "May 2019 - January 2020  (9 months)\n",
+      "Greater New York City Area\n",
+      "I founded untapt in October 2013; emerged from stealth in 2014 and went\n",
+      "into production with first product in 2015. In May 2019, I handed over CEO\n",
+      "responsibilities to Gareth Moody, previously the Chief Revenue Officer, shifting\n",
+      "my focus to the technology and product.\n",
+      "Our core invention is an Artificial Neural Network that uses Deep Learning /\n",
+      "NLP to understand the fit between candidates and roles.\n",
+      "Our SaaS products are used in the Recruitment Industry to connect people\n",
+      "with jobs in a highly scalable way. Our products are also used by Corporations\n",
+      "for internal and external hiring at high volume. We have strong SaaS metrics\n",
+      "and trends, and a growing number of bellwether clients.\n",
+      "Our Deep Learning / NLP models are developed in Python using Google\n",
+      "TensorFlow. Our tech stack is React / Redux and Angular HTML5 front-end\n",
+      "with Python / Flask back-end and MongoDB database. We are deployed on\n",
+      "the Google Cloud Platform using Kubernetes container orchestration.\n",
+      "Interview at NASDAQ: https://www.pscp.tv/w/1mnxeoNrEvZGX\n",
+      "Founder, CEO\n",
+      "October 2013 - May 2019  (5 years 8 months)\n",
+      "Greater New York City Area\n",
+      "I founded untapt in October 2013; emerged from stealth in 2014 and went into\n",
+      "production with first product in 2015.\n",
+      "Our core invention is an Artificial Neural Network that uses Deep Learning /\n",
+      "NLP to understand the fit between candidates and roles.\n",
+      "Our SaaS products are used in the Recruitment Industry to connect people\n",
+      "with jobs in a highly scalable way. Our products are also used by Corporations\n",
+      "for internal and external hiring at high volume. We have strong SaaS metrics\n",
+      "and trends, and a growing number of bellwether clients.\n",
+      "  Page 3 of 5   \n",
+      "Our Deep Learning / NLP models are developed in Python using Google\n",
+      "TensorFlow. Our tech stack is React / Redux and Angular HTML5 front-end\n",
+      "with Python / Flask back-end and MongoDB database. We are deployed on\n",
+      "the Google Cloud Platform using Kubernetes container orchestration.\n",
+      "-- Graduate of FinTech Innovation Lab\n",
+      "-- American Banker Top 20 Company To Watch\n",
+      "-- Voted AWS startup most likely to grow exponentially\n",
+      "-- Forbes contributor\n",
+      "More at https://www.untapt.com\n",
+      "Interview at NASDAQ: https://www.pscp.tv/w/1mnxeoNrEvZGX\n",
+      "In Fast Company: https://www.fastcompany.com/3067339/how-artificial-\n",
+      "intelligence-is-changing-the-way-companies-hire\n",
+      "JPMorgan Chase\n",
+      "11 years 6 months\n",
+      "Managing Director\n",
+      "May 2011 - March 2013  (1 year 11 months)\n",
+      "Head of Technology for the Credit Portfolio Group and Hedge Fund Credit in\n",
+      "the JPMorgan Investment Bank.\n",
+      "Led a team of 300 Java and Python software developers across NY, Houston,\n",
+      "London, Glasgow and India. Responsible for counterparty exposure, CVA\n",
+      "and risk management platforms, including simulation engines in Python that\n",
+      "calculate counterparty credit risk for the firm's Derivatives portfolio.\n",
+      "Managed the electronic trading limits initiative, and the Credit Stress program\n",
+      "which calculates risk information under stressed conditions. Jointly responsible\n",
+      "for Market Data and batch infrastructure across Risk.\n",
+      "Executive Director\n",
+      "January 2007 - May 2011  (4 years 5 months)\n",
+      "From Jan 2008:\n",
+      "Chief Business Technologist for the Credit Portfolio Group and Hedge Fund\n",
+      "Credit in the JPMorgan Investment Bank, building Java and Python solutions\n",
+      "and managing a team of full stack developers.\n",
+      "2007:\n",
+      "  Page 4 of 5   \n",
+      "Responsible for Credit Risk Limits Monitoring infrastructure for Derivatives and\n",
+      "Cash Securities, developed in Java / Javascript / HTML.\n",
+      "VP\n",
+      "July 2004 - December 2006  (2 years 6 months)\n",
+      "Managed Collateral, Netting and Legal documentation technology across\n",
+      "Derivatives, Securities and Traditional Credit Products, including Java, Oracle,\n",
+      "SQL based platforms\n",
+      "VP\n",
+      "October 2001 - June 2004  (2 years 9 months)\n",
+      "Full stack developer, then manager for Java cross-product risk management\n",
+      "system in Credit Markets Technology\n",
+      "Cygnifi\n",
+      "Project Leader\n",
+      "January 2000 - September 2001  (1 year 9 months)\n",
+      "Full stack developer and engineering lead, developing Java and Javascript\n",
+      "platform to risk manage Interest Rate Derivatives at this FInTech startup and\n",
+      "JPMorgan spin-off.\n",
+      "JPMorgan\n",
+      "Associate\n",
+      "July 1997 - December 1999  (2 years 6 months)\n",
+      "Full stack developer for Exotic and Flow Interest Rate Derivatives risk\n",
+      "management system in London, New York and Tokyo\n",
+      "IBM\n",
+      "Software Developer\n",
+      "August 1995 - June 1997  (1 year 11 months)\n",
+      "Java and Smalltalk developer with IBM Global Services; taught IBM classes on\n",
+      "Smalltalk and Object Technology in the UK and around Europe\n",
+      "Education\n",
+      "University of Oxford\n",
+      "Physics   · (1992 - 1995)\n",
+      "  Page 5 of 5\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(linkedin)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"me/summary.txt\", \"r\", encoding = \"utf-8\") as f:\n",
+    "    summary = f.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "name = \"Ed Donner\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = f\"You are acting as {name}. You are answering questions on {name}'s website, \\\n",
+    "particularly questions related to {name}'s career, background, skills and experience. \\\n",
+    "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n",
+    "You are given a summary of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n",
+    "Be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "If you don't know the answer, say so.\"\n",
+    "\n",
+    "system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"You are acting as Ed Donner. You are answering questions on Ed Donner's website, particularly questions related to Ed Donner's career, background, skills and experience. Your responsibility is to represent Ed Donner for interactions on the website as faithfully as possible. You are given a summary of Ed Donner's background and LinkedIn profile which you can use to answer questions. Be professional and engaging, as if talking to a potential client or future employer who came across the website. If you don't know the answer, say so.\\n\\n## Summary:\\nMy name is Ed Donner. I'm an entrepreneur, software engineer and data scientist. I'm originally from London, England, but I moved to NYC in 2000.\\nI love all foods, particularly French food, but strangely I'm repelled by almost all forms of cheese. I'm not allergic, I just hate the taste! I make an exception for cream cheese and mozarella though - cheesecake and pizza are the greatest.\\n\\n## LinkedIn Profile:\\n\\xa0 \\xa0\\nContact\\ned.donner@gmail.com\\nwww.linkedin.com/in/eddonner\\n(LinkedIn)\\nedwarddonner.com  (Personal)\\nTop Skills\\nCTO\\nLarge Language Models (LLM)\\nPyTorch\\nPatents\\nApparatus for determining role\\nfitness while eliminating unwanted\\nbiasEd Donner\\nCo-Founder & CTO at Nebula.io, repeat Co-Founder of AI startups,\\nspeaker & advisor on Gen AI and LLM Engineering\\nNew York, New York, United States\\nSummary\\nI’m a technology leader and entrepreneur. I'm applying AI to a field\\nwhere it can make a massive impact: helping people discover their\\npotential and pursue their reason for being. But at my core, I’m a\\nsoftware engineer and a scientist. I learned how to code aged 8 and\\nstill spend weekends experimenting with Large Language Models\\nand writing code (rather badly). If you’d like to join us to show me\\nhow it’s done.. message me!\\nAs a work-hobby, I absolutely love giving talks about Gen AI and\\nLLMs. I'm the author of a best-selling, top-rated Udemy course\\non LLM Engineering, and I speak at O'Reilly Live Events and\\nODSC workshops. It brings me great joy to help others unlock the\\nastonishing power of LLMs.\\nI spent most of my career at JPMorgan building software for financial\\nmarkets. I worked in London, Tokyo and New York. I became an MD\\nrunning a global organization of 300. Then I left to start my own AI\\nbusiness, untapt, to solve the problem that had plagued me at JPM -\\nwhy is so hard to hire engineers?\\nAt untapt we worked with GQR, one of the world's fastest growing\\nrecruitment firms. We collaborated on a patented invention in AI\\nand talent. Our skills were perfectly complementary - AI leaders vs\\nrecruitment leaders - so much so, that we decided to join forces. In\\n2020, untapt was acquired by GQR’s parent company and Nebula\\nwas born.\\nI’m now Co-Founder and CTO for Nebula, responsible for software\\nengineering and data science.  Our stack is Python/Flask, React,\\nMongo, ElasticSearch, with Kubernetes on GCP. Our 'secret sauce'\\nis our use of Gen AI and proprietary LLMs. If any of this sounds\\ninteresting - we should talk!\\n\\xa0 Page 1 of 5\\xa0 \\xa0\\nExperience\\nNebula.io\\nCo-Founder & CTO\\nJune 2021\\xa0-\\xa0Present\\xa0 (3 years 10 months)\\nNew York, New York, United States\\nI’m the co-founder and CTO of Nebula.io. We help recruiters source,\\nunderstand, engage and manage talent, using Generative AI / proprietary\\nLLMs. Our patented model matches people with roles with greater accuracy\\nand speed than previously imaginable — no keywords required.\\nOur long term goal is to help people discover their potential and pursue their\\nreason for being, motivated by a concept called Ikigai. We help people find\\nroles where they will be most fulfilled and successful; as a result, we will raise\\nthe level of human prosperity. It sounds grandiose, but since 77% of people\\ndon’t consider themselves inspired or engaged at work, it’s completely within\\nour reach.\\nSimplified.Travel\\nAI Advisor\\nFebruary 2025\\xa0-\\xa0Present\\xa0 (2 months)\\nSimplified Travel is empowering destinations to deliver unforgettable, data-\\ndriven journeys at scale.\\nI'm giving AI advice to enable highly personalized itinerary solutions for DMOs,\\nhotels and tourism organizations, enhancing traveler experiences.\\nGQR Global Markets\\nChief Technology Officer\\nJanuary 2020\\xa0-\\xa0Present\\xa0 (5 years 3 months)\\nNew York, New York, United States\\nAs CTO of parent company Wynden Stark, I'm also responsible for innovation\\ninitiatives at GQR.\\nWynden Stark\\nChief Technology Officer\\nJanuary 2020\\xa0-\\xa0Present\\xa0 (5 years 3 months)\\nNew York, New York, United States\\nWith the acquisition of untapt, I transitioned to Chief Technology Officer for the\\nWynden Stark Group, responsible for Data Science and Engineering.\\n\\xa0 Page 2 of 5\\xa0 \\xa0\\nuntapt\\n6 years 4 months\\nFounder, CTO\\nMay 2019\\xa0-\\xa0January 2020\\xa0 (9 months)\\nGreater New York City Area\\nI founded untapt in October 2013; emerged from stealth in 2014 and went\\ninto production with first product in 2015. In May 2019, I handed over CEO\\nresponsibilities to Gareth Moody, previously the Chief Revenue Officer, shifting\\nmy focus to the technology and product.\\nOur core invention is an Artificial Neural Network that uses Deep Learning /\\nNLP to understand the fit between candidates and roles.\\nOur SaaS products are used in the Recruitment Industry to connect people\\nwith jobs in a highly scalable way. Our products are also used by Corporations\\nfor internal and external hiring at high volume. We have strong SaaS metrics\\nand trends, and a growing number of bellwether clients.\\nOur Deep Learning / NLP models are developed in Python using Google\\nTensorFlow. Our tech stack is React / Redux and Angular HTML5 front-end\\nwith Python / Flask back-end and MongoDB database. We are deployed on\\nthe Google Cloud Platform using Kubernetes container orchestration.\\nInterview at NASDAQ: https://www.pscp.tv/w/1mnxeoNrEvZGX\\nFounder, CEO\\nOctober 2013\\xa0-\\xa0May 2019\\xa0 (5 years 8 months)\\nGreater New York City Area\\nI founded untapt in October 2013; emerged from stealth in 2014 and went into\\nproduction with first product in 2015.\\nOur core invention is an Artificial Neural Network that uses Deep Learning /\\nNLP to understand the fit between candidates and roles.\\nOur SaaS products are used in the Recruitment Industry to connect people\\nwith jobs in a highly scalable way. Our products are also used by Corporations\\nfor internal and external hiring at high volume. We have strong SaaS metrics\\nand trends, and a growing number of bellwether clients.\\n\\xa0 Page 3 of 5\\xa0 \\xa0\\nOur Deep Learning / NLP models are developed in Python using Google\\nTensorFlow. Our tech stack is React / Redux and Angular HTML5 front-end\\nwith Python / Flask back-end and MongoDB database. We are deployed on\\nthe Google Cloud Platform using Kubernetes container orchestration.\\n-- Graduate of FinTech Innovation Lab\\n-- American Banker Top 20 Company To Watch\\n-- Voted AWS startup most likely to grow exponentially\\n-- Forbes contributor\\nMore at https://www.untapt.com\\nInterview at NASDAQ: https://www.pscp.tv/w/1mnxeoNrEvZGX\\nIn Fast Company: https://www.fastcompany.com/3067339/how-artificial-\\nintelligence-is-changing-the-way-companies-hire\\nJPMorgan Chase\\n11 years 6 months\\nManaging Director\\nMay 2011\\xa0-\\xa0March 2013\\xa0 (1 year 11 months)\\nHead of Technology for the Credit Portfolio Group and Hedge Fund Credit in\\nthe JPMorgan Investment Bank.\\nLed a team of 300 Java and Python software developers across NY, Houston,\\nLondon, Glasgow and India. Responsible for counterparty exposure, CVA\\nand risk management platforms, including simulation engines in Python that\\ncalculate counterparty credit risk for the firm's Derivatives portfolio.\\nManaged the electronic trading limits initiative, and the Credit Stress program\\nwhich calculates risk information under stressed conditions. Jointly responsible\\nfor Market Data and batch infrastructure across Risk.\\nExecutive Director\\nJanuary 2007\\xa0-\\xa0May 2011\\xa0 (4 years 5 months)\\nFrom Jan 2008:\\nChief Business Technologist for the Credit Portfolio Group and Hedge Fund\\nCredit in the JPMorgan Investment Bank, building Java and Python solutions\\nand managing a team of full stack developers.\\n2007:\\n\\xa0 Page 4 of 5\\xa0 \\xa0\\nResponsible for Credit Risk Limits Monitoring infrastructure for Derivatives and\\nCash Securities, developed in Java / Javascript / HTML.\\nVP\\nJuly 2004\\xa0-\\xa0December 2006\\xa0 (2 years 6 months)\\nManaged Collateral, Netting and Legal documentation technology across\\nDerivatives, Securities and Traditional Credit Products, including Java, Oracle,\\nSQL based platforms\\nVP\\nOctober 2001\\xa0-\\xa0June 2004\\xa0 (2 years 9 months)\\nFull stack developer, then manager for Java cross-product risk management\\nsystem in Credit Markets Technology\\nCygnifi\\nProject Leader\\nJanuary 2000\\xa0-\\xa0September 2001\\xa0 (1 year 9 months)\\nFull stack developer and engineering lead, developing Java and Javascript\\nplatform to risk manage Interest Rate Derivatives at this FInTech startup and\\nJPMorgan spin-off.\\nJPMorgan\\nAssociate\\nJuly 1997\\xa0-\\xa0December 1999\\xa0 (2 years 6 months)\\nFull stack developer for Exotic and Flow Interest Rate Derivatives risk\\nmanagement system in London, New York and Tokyo\\nIBM\\nSoftware Developer\\nAugust 1995\\xa0-\\xa0June 1997\\xa0 (1 year 11 months)\\nJava and Smalltalk developer with IBM Global Services; taught IBM classes on\\nSmalltalk and Object Technology in the UK and around Europe\\nEducation\\nUniversity of Oxford\\nPhysics\\xa0 \\xa0·\\xa0(1992\\xa0-\\xa01995)\\n\\xa0 Page 5 of 5\\n\\nWith this context, please chat with the user, always staying in character as Ed Donner.\""
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "system_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Special note for people not using OpenAI\n",
+    "\n",
+    "Some providers, like Groq, might give an error when you send your second message in the chat.\n",
+    "\n",
+    "This is because Gradio shoves some extra fields into the history object. OpenAI doesn't mind; but some other models complain.\n",
+    "\n",
+    "If this happens, the solution is to add this first line to the chat() function above. It cleans up the history variable:\n",
+    "\n",
+    "```python\n",
+    "history = [{\"role\": h[\"role\"], \"content\": h[\"content\"]} for h in history]\n",
+    "```\n",
+    "\n",
+    "You may need to add this in other chat() callback functions in the future, too."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7860\n",
+      "* To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gr.ChatInterface(chat, type=\"messages\").launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## A lot is about to happen...\n",
+    "\n",
+    "1. Be able to ask an LLM to evaluate an answer\n",
+    "2. Be able to rerun if the answer fails evaluation\n",
+    "3. Put this together into 1 workflow\n",
+    "\n",
+    "All without any Agentic framework!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a Pydantic model for the Evaluation\n",
+    "\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "class Evaluation(BaseModel):\n",
+    "    is_acceptable: bool\n",
+    "    feedback: str\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "evaluator_system_prompt = f\"You are an evaluator that decides whether a response to a question is acceptable. \\\n",
+    "You are provided with a conversation between a User and an Agent. Your task is to decide whether the Agent's latest response is acceptable quality. \\\n",
+    "The Agent is playing the role of {name} and is representing {name} on their website. \\\n",
+    "The Agent has been instructed to be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "The Agent has been provided with context on {name} in the form of their summary and LinkedIn details. Here's the information:\"\n",
+    "\n",
+    "evaluator_system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "evaluator_system_prompt += f\"With this context, please evaluate the latest response, replying with whether the response is acceptable and your feedback.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluator_user_prompt(reply, message, history):\n",
+    "    user_prompt = f\"Here's the conversation between the User and the Agent: \\n\\n{history}\\n\\n\"\n",
+    "    user_prompt += f\"Here's the latest message from the User: \\n\\n{message}\\n\\n\"\n",
+    "    user_prompt += f\"Here's the latest response from the Agent: \\n\\n{reply}\\n\\n\"\n",
+    "    user_prompt += \"Please evaluate the response, replying with whether it is acceptable and your feedback.\"\n",
+    "    return user_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import os\n",
+    "# gemini = OpenAI(\n",
+    "#     api_key=os.getenv(\"OPENAI_API_KEY\"), \n",
+    "#     base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    "# )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluate(reply, message, history) -> Evaluation:\n",
+    "\n",
+    "    messages = [{\"role\": \"system\", \"content\": evaluator_system_prompt}] + [{\"role\": \"user\", \"content\": evaluator_user_prompt(reply, message, history)}]\n",
+    "    response = openai.chat.completions.parse(model=\"gpt-4o-mini\", messages=messages, response_format=Evaluation)\n",
+    "    return response.choices[0].message.parsed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"system\", \"content\": system_prompt}] + [{\"role\": \"user\", \"content\": \"do you hold a patent?\"}]\n",
+    "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+    "reply = response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Yes, I hold a patent related to an invention that focuses on using AI in the recruitment process to eliminate bias and enhance the fit between candidates and roles. This was a result of my work with untapt, where we collaborated with recruitment leaders to integrate our AI-driven solutions. If you're interested in learning more about it or the technology behind it, feel free to ask!\""
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "reply"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Evaluation(is_acceptable=True, feedback=\"The Agent's response is of acceptable quality. It provides a clear and concise answer to the user's question about holding a patent, offering specific details about the patent's focus and context. Additionally, the response invites further questions, which is engaging and professional, in line with the character of Ed Donner. Overall, it appropriately represents Ed's expertise and background.\")"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluate(reply, \"do you hold a patent?\", messages[:1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rerun(reply, message, history, feedback):\n",
+    "    updated_system_prompt = system_prompt + \"\\n\\n## Previous answer rejected\\nYou just tried to reply, but the quality control rejected your reply\\n\"\n",
+    "    updated_system_prompt += f\"## Your attempted answer:\\n{reply}\\n\\n\"\n",
+    "    updated_system_prompt += f\"## Reason for rejection:\\n{feedback}\\n\\n\"\n",
+    "    messages = [{\"role\": \"system\", \"content\": updated_system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    if \"patent\" in message:\n",
+    "        system = system_prompt + \"\\n\\nEverything in your reply needs to be in pig latin - \\\n",
+    "              it is mandatory that you respond only and entirely in pig latin\"\n",
+    "    else:\n",
+    "        system = system_prompt\n",
+    "    messages = [{\"role\": \"system\", \"content\": system}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+    "    reply =response.choices[0].message.content\n",
+    "\n",
+    "    evaluation = evaluate(reply, message, history)\n",
+    "    \n",
+    "    if evaluation.is_acceptable:\n",
+    "        print(\"Passed evaluation - returning reply\")\n",
+    "    else:\n",
+    "        print(\"Failed evaluation - retrying\")\n",
+    "        print(evaluation.feedback)\n",
+    "        reply = rerun(reply, message, history, evaluation.feedback)       \n",
+    "    return reply"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gr.ChatInterface(chat, type=\"messages\").launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agents (3.12.5)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

4_lab4.ipynb

@@ -0,0 +1,568 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## The first big project - Professionally You!\n",
+    "\n",
+    "### And, Tool use.\n",
+    "\n",
+    "### But first: introducing Pushover\n",
+    "\n",
+    "Pushover is a nifty tool for sending Push Notifications to your phone.\n",
+    "\n",
+    "It's super easy to set up and install!\n",
+    "\n",
+    "Simply visit https://pushover.net/ and click 'Login or Signup' on the top right to sign up for a free account, and create your API keys.\n",
+    "\n",
+    "Once you've signed up, on the home screen, click \"Create an Application/API Token\", and give it any name (like Agents) and click Create Application.\n",
+    "\n",
+    "Then add 2 lines to your `.env` file:\n",
+    "\n",
+    "PUSHOVER_USER=_put the key that's on the top right of your Pushover home screen and probably starts with a u_  \n",
+    "PUSHOVER_TOKEN=_put the key when you click into your new application called Agents (or whatever) and probably starts with an a_\n",
+    "\n",
+    "Remember to save your `.env` file, and run `load_dotenv(override=True)` after saving, to set your environment variables.\n",
+    "\n",
+    "Finally, click \"Add Phone, Tablet or Desktop\" to install on your phone."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "import json\n",
+    "import os\n",
+    "import requests\n",
+    "from pypdf import PdfReader\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The usual start\n",
+    "\n",
+    "load_dotenv(override=True)\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pushover user found and starts with u\n",
+      "Pushover token found and starts with a\n"
+     ]
+    }
+   ],
+   "source": [
+    "# For pushover\n",
+    "\n",
+    "pushover_user = os.getenv(\"PUSHOVER_USER\")\n",
+    "pushover_token = os.getenv(\"PUSHOVER_TOKEN\")\n",
+    "pushover_url = \"https://api.pushover.net/1/messages.json\"\n",
+    "\n",
+    "if pushover_user:\n",
+    "    print(f\"Pushover user found and starts with {pushover_user[0]}\")\n",
+    "else:\n",
+    "    print(\"Pushover user not found\")\n",
+    "\n",
+    "if pushover_token:\n",
+    "    print(f\"Pushover token found and starts with {pushover_token[0]}\")\n",
+    "else:\n",
+    "    print(\"Pushover token not found\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def push(message):\n",
+    "    print(f\"Push: {message}\")\n",
+    "    payload = {\"user\": pushover_user, \"token\": pushover_token, \"message\": message}\n",
+    "    requests.post(pushover_url, data=payload)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Push: HEY!!\n"
+     ]
+    }
+   ],
+   "source": [
+    "push(\"HEY!!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This is generally used to record user details if user wants to get in touch.\n",
+    "def record_user_details(email, name=\"Name not provided\", notes=\"not provided\"):\n",
+    "    push(f\"Recording interest from {name} with email {email} and notes {notes}\")\n",
+    "    return {\"recorded\": \"ok\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# this is when user ask something out of the box question, then it will send you a notification.\n",
+    "def record_unknown_question(question):\n",
+    "    push(f\"Recording {question} asked that I couldn't answer\")\n",
+    "    return {\"recorded\": \"ok\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "record_user_details_json = {\n",
+    "    \"name\": \"record_user_details\",\n",
+    "    \"description\": \"Use this tool to record that a user is interested in being in touch and provided an email address\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"email\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The email address of this user\"\n",
+    "            },\n",
+    "            \"name\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The user's name, if they provided it\"\n",
+    "            }\n",
+    "            ,\n",
+    "            \"notes\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"Any additional information about the conversation that's worth recording to give context\"\n",
+    "            }\n",
+    "        },\n",
+    "        \"required\": [\"email\"],\n",
+    "        \"additionalProperties\": False\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "record_unknown_question_json = {\n",
+    "    \"name\": \"record_unknown_question\",\n",
+    "    \"description\": \"Always use this tool to record any question that couldn't be answered as you didn't know the answer\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"question\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The question that couldn't be answered\"\n",
+    "            },\n",
+    "        },\n",
+    "        \"required\": [\"question\"],\n",
+    "        \"additionalProperties\": False\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [{\"type\": \"function\", \"function\": record_user_details_json},\n",
+    "        {\"type\": \"function\", \"function\": record_unknown_question_json}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'type': 'function',\n",
+       "  'function': {'name': 'record_user_details',\n",
+       "   'description': 'Use this tool to record that a user is interested in being in touch and provided an email address',\n",
+       "   'parameters': {'type': 'object',\n",
+       "    'properties': {'email': {'type': 'string',\n",
+       "      'description': 'The email address of this user'},\n",
+       "     'name': {'type': 'string',\n",
+       "      'description': \"The user's name, if they provided it\"},\n",
+       "     'notes': {'type': 'string',\n",
+       "      'description': \"Any additional information about the conversation that's worth recording to give context\"}},\n",
+       "    'required': ['email'],\n",
+       "    'additionalProperties': False}}},\n",
+       " {'type': 'function',\n",
+       "  'function': {'name': 'record_unknown_question',\n",
+       "   'description': \"Always use this tool to record any question that couldn't be answered as you didn't know the answer\",\n",
+       "   'parameters': {'type': 'object',\n",
+       "    'properties': {'question': {'type': 'string',\n",
+       "      'description': \"The question that couldn't be answered\"}},\n",
+       "    'required': ['question'],\n",
+       "    'additionalProperties': False}}}]"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This function can take a list of tool calls, and run them. This is the IF statement!!\n",
+    "\n",
+    "def handle_tool_calls(tool_calls):\n",
+    "    results = []\n",
+    "    for tool_call in tool_calls:\n",
+    "        tool_name = tool_call.function.name\n",
+    "        arguments = json.loads(tool_call.function.arguments)\n",
+    "        print(f\"Tool called: {tool_name}\", flush=True)\n",
+    "\n",
+    "        # THE BIG IF STATEMENT!!!\n",
+    "\n",
+    "        if tool_name == \"record_user_details\":\n",
+    "            result = record_user_details(**arguments)\n",
+    "        elif tool_name == \"record_unknown_question\":\n",
+    "            result = record_unknown_question(**arguments)\n",
+    "\n",
+    "        results.append({\"role\": \"tool\",\"content\": json.dumps(result),\"tool_call_id\": tool_call.id})\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Push: Recording this is a really hard question asked that I couldn't answer\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'recorded': 'ok'}"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "globals()[\"record_unknown_question\"](\"this is a really hard question\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This is a more elegant way that avoids the IF statement.\n",
+    "\n",
+    "def handle_tool_calls(tool_calls):\n",
+    "    results = []\n",
+    "    for tool_call in tool_calls:\n",
+    "        tool_name = tool_call.function.name\n",
+    "        arguments = json.loads(tool_call.function.arguments)\n",
+    "        print(f\"Tool called: {tool_name}\", flush=True)\n",
+    "        tool = globals().get(tool_name)\n",
+    "        result = tool(**arguments) if tool else {}\n",
+    "        results.append({\"role\": \"tool\",\"content\": json.dumps(result),\"tool_call_id\": tool_call.id})\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reader = PdfReader(\"me/linkedin.pdf\")\n",
+    "linkedin = \"\"\n",
+    "for page in reader.pages:\n",
+    "    text = page.extract_text()\n",
+    "    if text:\n",
+    "        linkedin += text\n",
+    "\n",
+    "with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
+    "    summary = f.read()\n",
+    "\n",
+    "name = \"Venkata Vikranth Jannatha\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = f\"You are acting as {name}. You are answering questions on {name}'s website, \\\n",
+    "particularly questions related to {name}'s career, background, skills and experience. \\\n",
+    "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n",
+    "You are given a summary of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n",
+    "Be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \\\n",
+    "If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. \"\n",
+    "\n",
+    "system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    done = False\n",
+    "    while not done:\n",
+    "\n",
+    "        # This is the call to the LLM - see that we pass in the tools json\n",
+    "\n",
+    "        response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages, tools=tools)\n",
+    "\n",
+    "        finish_reason = response.choices[0].finish_reason\n",
+    "        print(finish_reason)\n",
+    "        \n",
+    "        # If the LLM wants to call a tool, we do that!\n",
+    "         \n",
+    "        if finish_reason==\"tool_calls\":\n",
+    "            message = response.choices[0].message\n",
+    "            tool_calls = message.tool_calls\n",
+    "            results = handle_tool_calls(tool_calls)\n",
+    "            messages.append(message)\n",
+    "            messages.extend(results)\n",
+    "        else:\n",
+    "            done = True\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7860\n",
+      "* To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "stop\n",
+      "stop\n",
+      "tool_calls\n",
+      "Tool called: record_unknown_question\n",
+      "Push: Recording do you have patent? asked that I couldn't answer\n",
+      "stop\n",
+      "tool_calls\n",
+      "Tool called: record_unknown_question\n",
+      "Push: Recording who is your favorite singer? asked that I couldn't answer\n",
+      "stop\n",
+      "stop\n",
+      "tool_calls\n",
+      "Tool called: record_user_details\n",
+      "Push: Recording interest from Name not provided with email vjannatha@gmail.com and notes not provided\n",
+      "stop\n"
+     ]
+    }
+   ],
+   "source": [
+    "gr.ChatInterface(chat).launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## And now for deployment\n",
+    "\n",
+    "This code is in `app.py`\n",
+    "\n",
+    "We will deploy to HuggingFace Spaces.\n",
+    "\n",
+    "Before you start: remember to update the files in the \"me\" directory - your LinkedIn profile and summary.txt - so that it talks about you! Also change `self.name = \"Ed Donner\"` in `app.py`..  \n",
+    "\n",
+    "Also check that there's no README file within the 1_foundations directory. If there is one, please delete it. The deploy process creates a new README file in this directory for you.\n",
+    "\n",
+    "1. Visit https://huggingface.co and set up an account  \n",
+    "2. From the Avatar menu on the top right, choose Access Tokens. Choose \"Create New Token\". Give it WRITE permissions - it needs to have WRITE permissions! Keep a record of your new key.  \n",
+    "3. In the Terminal, run: `uv tool install 'huggingface_hub[cli]'` to install the HuggingFace tool, then `hf auth login --token YOUR_TOKEN_HERE`, like `hf auth login --token hf_xxxxxx`, to login at the command line with your key. Afterwards, run `hf auth whoami` to check you're logged in  \n",
+    "4. Take your new token and add it to your .env file: `HF_TOKEN=hf_xxx` for the future\n",
+    "5. From the 1_foundations folder, enter: `uv run gradio deploy` \n",
+    "6. Follow its instructions: name it \"career_conversation\", specify app.py, choose cpu-basic as the hardware, say Yes to needing to supply secrets, provide your openai api key, your pushover user and token, and say \"no\" to github actions.  \n",
+    "\n",
+    "Thank you Robert, James, Martins, Andras and Priya for these tips.  \n",
+    "Please read the next 2 sections - how to change your Secrets, and how to redeploy your Space (you may need to delete the README.md that gets created in this 1_foundations directory).\n",
+    "\n",
+    "#### More about these secrets:\n",
+    "\n",
+    "If you're confused by what's going on with these secrets: it just wants you to enter the key name and value for each of your secrets -- so you would enter:  \n",
+    "`OPENAI_API_KEY`  \n",
+    "Followed by:  \n",
+    "`sk-proj-...`  \n",
+    "\n",
+    "And if you don't want to set secrets this way, or something goes wrong with it, it's no problem - you can change your secrets later:  \n",
+    "1. Log in to HuggingFace website  \n",
+    "2. Go to your profile screen via the Avatar menu on the top right  \n",
+    "3. Select the Space you deployed  \n",
+    "4. Click on the Settings wheel on the top right  \n",
+    "5. You can scroll down to change your secrets (Variables and Secrets section), delete the space, etc.\n",
+    "\n",
+    "#### And now you should be deployed!\n",
+    "\n",
+    "If you want to completely replace everything and start again with your keys, you may need to delete the README.md that got created in this 1_foundations folder.\n",
+    "\n",
+    "Here is mine: https://huggingface.co/spaces/ed-donner/Career_Conversation\n",
+    "\n",
+    "I just got a push notification that a student asked me how they can become President of their country 😂😂\n",
+    "\n",
+    "For more information on deployment:\n",
+    "\n",
+    "https://www.gradio.app/guides/sharing-your-app#hosting-on-hf-spaces\n",
+    "\n",
+    "To delete your Space in the future:  \n",
+    "1. Log in to HuggingFace\n",
+    "2. From the Avatar menu, select your profile\n",
+    "3. Click on the Space itself and select the settings wheel on the top right\n",
+    "4. Scroll to the Delete section at the bottom\n",
+    "5. ALSO: delete the README file that Gradio may have created inside this 1_foundations folder (otherwise it won't ask you the questions the next time you do a gradio deploy)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">• First and foremost, deploy this for yourself! It's a real, valuable tool - the future resume..<br/>\n",
+    "            • Next, improve the resources - add better context about yourself. If you know RAG, then add a knowledge base about you.<br/>\n",
+    "            • Add in more tools! You could have a SQL database with common Q&A that the LLM could read and write from?<br/>\n",
+    "            • Bring in the Evaluator from the last lab, and add other Agentic patterns.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">Aside from the obvious (your career alter-ego) this has business applications in any situation where you need an AI assistant with domain expertise and an ability to interact with the real world.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agents (3.12.5)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

README.md

@@ -1,12 +1,6 @@
 ---
-title: Career Conversations
-emoji: 😻
-colorFrom: indigo
-colorTo: indigo
-sdk: gradio
-sdk_version: 6.1.0
+title: career_conversations
 app_file: app.py
-pinned: false
+sdk: gradio
+sdk_version: 5.49.1
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,164 @@
+from dotenv import load_dotenv
+from openai import OpenAI
+import json
+import os
+import requests
+from pypdf import PdfReader
+import gradio as gr
+
+
+load_dotenv(override=True)
+
+def push(text):
+    requests.post(
+        "https://api.pushover.net/1/messages.json",
+        data={
+            "token": os.getenv("PUSHOVER_TOKEN"),
+            "user": os.getenv("PUSHOVER_USER"),
+            "message": text,
+        }
+    )
+
+
+def record_user_details(email, name="Name not provided", notes="not provided"):
+    push(f"Recording {name} with email {email} and notes {notes}")
+    return {"recorded": "ok"}
+
+def record_unknown_question(question):
+    push(f"Recording {question}")
+    return {"recorded": "ok"}
+
+record_user_details_json = {
+    "name": "record_user_details",
+    "description": "Use this tool to record that a user is interested in being in touch and provided an email address",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "email": {
+                "type": "string",
+                "description": "The email address of this user"
+            },
+            "name": {
+                "type": "string",
+                "description": "The user's name, if they provided it"
+            }
+            ,
+            "notes": {
+                "type": "string",
+                "description": "Any additional information about the conversation that's worth recording to give context"
+            }
+        },
+        "required": ["email"],
+        "additionalProperties": False
+    }
+}
+
+record_unknown_question_json = {
+    "name": "record_unknown_question",
+    "description": "Always use this tool to record any question that couldn't be answered as you didn't know the answer",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "question": {
+                "type": "string",
+                "description": "The question that couldn't be answered"
+            },
+        },
+        "required": ["question"],
+        "additionalProperties": False
+    }
+}
+
+tools = [{"type": "function", "function": record_user_details_json},
+        {"type": "function", "function": record_unknown_question_json}]
+
+
+class Me:
+
+    def __init__(self):
+        self.openai = OpenAI()
+        self.name = "Venkata Vikranth Janantha"
+        reader = PdfReader("me/linkedin.pdf")
+        self.linkedin = ""
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                self.linkedin += text
+        with open("me/summary.txt", "r", encoding="utf-8") as f:
+            self.summary = f.read()
+
+
+    def handle_tool_call(self, tool_calls):
+        results = []
+        for tool_call in tool_calls:
+            tool_name = tool_call.function.name
+            arguments = json.loads(tool_call.function.arguments)
+            print(f"Tool called: {tool_name}", flush=True)
+            tool = globals().get(tool_name)
+            result = tool(**arguments) if tool else {}
+            results.append({"role": "tool","content": json.dumps(result),"tool_call_id": tool_call.id})
+        return results
+    
+    def system_prompt(self):
+        system_prompt = f"You are acting as {self.name}. You are answering questions on {self.name}'s website, \
+particularly questions related to {self.name}'s career, background, skills and experience. \
+Your responsibility is to represent {self.name} for interactions on the website as faithfully as possible. \
+You are given a summary of {self.name}'s background and LinkedIn profile which you can use to answer questions. \
+Be professional and engaging, as if talking to a potential client or future employer who came across the website. \
+If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \
+If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. "
+
+        system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n"
+        system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}."
+        return system_prompt
+
+    def _normalize_history(self, history):
+        """Convert Gradio chat history into OpenAI chat messages."""
+        if not history:
+            return []
+
+        allowed_roles = {"system", "user", "assistant", "tool", "function", "developer"}
+
+        # Newer Gradio can provide OpenAI-style message dicts already
+        if isinstance(history, list) and history and isinstance(history[0], dict):
+            normalized = []
+            for item in history:
+                role = item.get("role")
+                content = item.get("content")
+                if role in allowed_roles and isinstance(content, str):
+                    normalized.append({"role": role, "content": content})
+            return normalized
+
+        # Legacy Gradio provides tuples: [(user_msg, assistant_msg), ...]
+        normalized = []
+        for pair in history:
+            if not (isinstance(pair, (list, tuple)) and len(pair) == 2):
+                continue
+            user_msg, assistant_msg = pair
+            if user_msg is not None and str(user_msg).strip() != "":
+                normalized.append({"role": "user", "content": str(user_msg)})
+            if assistant_msg is not None and str(assistant_msg).strip() != "":
+                normalized.append({"role": "assistant", "content": str(assistant_msg)})
+        return normalized
+    
+    def chat(self, message, history):
+        history_messages = self._normalize_history(history)
+        messages = [{"role": "system", "content": self.system_prompt()}] + history_messages + [{"role": "user", "content": message}]
+        done = False
+        while not done:
+            response = self.openai.chat.completions.create(model="gpt-4o-mini", messages=messages, tools=tools)
+            if response.choices[0].finish_reason=="tool_calls":
+                message = response.choices[0].message
+                tool_calls = message.tool_calls
+                results = self.handle_tool_call(tool_calls)
+                messages.append(message)
+                messages.extend(results)
+            else:
+                done = True
+        return response.choices[0].message.content
+    
+
+if __name__ == "__main__":
+    me = Me()
+    gr.ChatInterface(me.chat).launch(share=True)
+    

community_contributions/1_foundations_using_gemini/1_lab1.ipynb

@@ -0,0 +1,406 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "gemini_api_key = os.getenv('GEMINI_API_KEY')\n",
+    "\n",
+    "if gemini_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {gemini_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "GEMINI_BASE_URL = \"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n",
+    "gemini = OpenAI(base_url=GEMINI_BASE_URL, api_key=google_api_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "model = \"gemini-2.5-flash-preview-05-20\"\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Pick a business area that might be worth exploring for an Agentic AI opportunity.\"}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.choices[0].message.content\n",
+    "\n",
+    "\n",
+    "display(Markdown(business_idea))\n",
+    "\n",
+    "# And repeat! In the next message, include the business idea within the message"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": f\"Present a pain-point in that {business_idea} industry - something challenging that might be ripe for an Agentic solution.\"}]\n",
+    "\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "pain_point = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(pain_point))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": f\"Propose an Agentic AI solution to the {pain_point} in the {business_idea} industry.\"}]\n",
+    "\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=model,\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "agentic_solution = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(agentic_solution))\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_foundations_using_gemini/2_lab2.ipynb

@@ -0,0 +1,492 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Note - update since the videos\n",
+    "\n",
+    "I've updated the model names to use the latest models below, like GPT 5 and Claude Sonnet 4.5. It's worth noting that these models can be quite slow - like 1-2 minutes - but they do a great job! Feel free to switch them for faster models if you'd prefer, like the ones I use in the video."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "# I've updated this with the latest model, but it can take some time because it likes to think!\n",
+    "# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins\n",
+    "\n",
+    "model_name = \"gpt-5-nano\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-sonnet-4-5\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.5-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Updated with the latest Open Source model from OpenAI\n",
+    "\n",
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"openai/gpt-oss-120b\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_foundations_using_gemini/3_lab3.ipynb

@@ -0,0 +1,382 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to Lab 3 for Week 1 Day 4\n",
+    "\n",
+    "Today we're going to build something with immediate value!\n",
+    "\n",
+    "In the folder `me` I've put a single file `linkedin.pdf` - it's a PDF download of my LinkedIn profile.\n",
+    "\n",
+    "Please replace it with yours!\n",
+    "\n",
+    "I've also made a file called `summary.txt`\n",
+    "\n",
+    "We're not going to use Tools just yet - we're going to add the tool tomorrow."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Looking up packages</h2>\n",
+    "            <span style=\"color:#00bfff;\">In this lab, we're going to use the wonderful Gradio package for building quick UIs, \n",
+    "            and we're also going to use the popular PyPDF PDF reader. You can get guides to these packages by asking \n",
+    "            ChatGPT or Claude, and you find all open-source packages on the repository <a href=\"https://pypi.org\">https://pypi.org</a>.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# If you don't know what any of these packages do - you can always ask ChatGPT for a guide!\n",
+    "\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from pypdf import PdfReader\n",
+    "import os\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)\n",
+    "GEMINI_BASE_URL = \"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n",
+    "gemini = OpenAI(base_url=GEMINI_BASE_URL, api_key=google_api_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reader = PdfReader(\"me/linkedin.pdf\")\n",
+    "linkedin = \"\"\n",
+    "for page in reader.pages:\n",
+    "    text = page.extract_text()\n",
+    "    if text:\n",
+    "        linkedin += text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(linkedin)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
+    "    summary = f.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "name = \"Harsh Patidar\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = f\"You are acting as {name}. You are answering questions on {name}'s website, \\\n",
+    "particularly questions related to {name}'s career, background, skills and experience. \\\n",
+    "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n",
+    "You are given a summary of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n",
+    "Be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "If you don't know the answer, say so.\"\n",
+    "\n",
+    "system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = \"gemini-2.5-flash-preview-05-20\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Special note for people not using OpenAI\n",
+    "\n",
+    "Some providers, like Groq, might give an error when you send your second message in the chat.\n",
+    "\n",
+    "This is because Gradio shoves some extra fields into the history object. OpenAI doesn't mind; but some other models complain.\n",
+    "\n",
+    "If this happens, the solution is to add this first line to the chat() function above. It cleans up the history variable:\n",
+    "\n",
+    "```python\n",
+    "history = [{\"role\": h[\"role\"], \"content\": h[\"content\"]} for h in history]\n",
+    "```\n",
+    "\n",
+    "You may need to add this in other chat() callback functions in the future, too."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gr.ChatInterface(chat, type=\"messages\").launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## A lot is about to happen...\n",
+    "\n",
+    "1. Be able to ask an LLM to evaluate an answer\n",
+    "2. Be able to rerun if the answer fails evaluation\n",
+    "3. Put this together into 1 workflow\n",
+    "\n",
+    "All without any Agentic framework!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a Pydantic model for the Evaluation\n",
+    "\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "class Evaluation(BaseModel):\n",
+    "    is_acceptable: bool\n",
+    "    feedback: str\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "evaluator_system_prompt = f\"You are an evaluator that decides whether a response to a question is acceptable. \\\n",
+    "You are provided with a conversation between a User and an Agent. Your task is to decide whether the Agent's latest response is acceptable quality. \\\n",
+    "The Agent is playing the role of {name} and is representing {name} on their website. \\\n",
+    "The Agent has been instructed to be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "The Agent has been provided with context on {name} in the form of their summary and LinkedIn details. Here's the information:\"\n",
+    "\n",
+    "evaluator_system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "evaluator_system_prompt += f\"With this context, please evaluate the latest response, replying with whether the response is acceptable and your feedback.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluator_user_prompt(reply, message, history):\n",
+    "    user_prompt = f\"Here's the conversation between the User and the Agent: \\n\\n{history}\\n\\n\"\n",
+    "    user_prompt += f\"Here's the latest message from the User: \\n\\n{message}\\n\\n\"\n",
+    "    user_prompt += f\"Here's the latest response from the Agent: \\n\\n{reply}\\n\\n\"\n",
+    "    user_prompt += \"Please evaluate the response, replying with whether it is acceptable and your feedback.\"\n",
+    "    return user_prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "gemini = OpenAI(\n",
+    "    api_key=os.getenv(\"GOOGLE_API_KEY\"), \n",
+    "    base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluate(reply, message, history) -> Evaluation:\n",
+    "\n",
+    "    messages = [{\"role\": \"system\", \"content\": evaluator_system_prompt}] + [{\"role\": \"user\", \"content\": evaluator_user_prompt(reply, message, history)}]\n",
+    "    response = gemini.beta.chat.completions.parse(model=model_name, messages=messages, response_format=Evaluation)\n",
+    "    return response.choices[0].message.parsed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"system\", \"content\": system_prompt}] + [{\"role\": \"user\", \"content\": \"do you hold a patent?\"}]\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "reply = response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reply"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "evaluate(reply, \"do you hold a patent?\", messages[:1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rerun(reply, message, history, feedback):\n",
+    "    updated_system_prompt = system_prompt + \"\\n\\n## Previous answer rejected\\nYou just tried to reply, but the quality control rejected your reply\\n\"\n",
+    "    updated_system_prompt += f\"## Your attempted answer:\\n{reply}\\n\\n\"\n",
+    "    updated_system_prompt += f\"## Reason for rejection:\\n{feedback}\\n\\n\"\n",
+    "    messages = [{\"role\": \"system\", \"content\": updated_system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(message, history):\n",
+    "    if \"patent\" in message:\n",
+    "        system = system_prompt + \"\\n\\nEverything in your reply needs to be in pig latin - \\\n",
+    "              it is mandatory that you respond only and entirely in pig latin\"\n",
+    "    else:\n",
+    "        system = system_prompt\n",
+    "    messages = [{\"role\": \"system\", \"content\": system}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    reply =response.choices[0].message.content\n",
+    "\n",
+    "    evaluation = evaluate(reply, message, history)\n",
+    "    \n",
+    "    if evaluation.is_acceptable:\n",
+    "        print(\"Passed evaluation - returning reply\")\n",
+    "    else:\n",
+    "        print(\"Failed evaluation - retrying\")\n",
+    "        print(evaluation.feedback)\n",
+    "        reply = rerun(reply, message, history, evaluation.feedback)       \n",
+    "    return reply"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gr.ChatInterface(chat, type=\"messages\").launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_foundations_using_gemini/4_lab4.ipynb

@@ -0,0 +1,464 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## The first big project - Professionally You!\n",
+    "\n",
+    "### And, Tool use.\n",
+    "\n",
+    "### But first: introducing Pushover\n",
+    "\n",
+    "Pushover is a nifty tool for sending Push Notifications to your phone.\n",
+    "\n",
+    "It's super easy to set up and install!\n",
+    "\n",
+    "Simply visit https://pushover.net/ and click 'Login or Signup' on the top right to sign up for a free account, and create your API keys.\n",
+    "\n",
+    "Once you've signed up, on the home screen, click \"Create an Application/API Token\", and give it any name (like Agents) and click Create Application.\n",
+    "\n",
+    "Then add 2 lines to your `.env` file:\n",
+    "\n",
+    "PUSHOVER_USER=_put the key that's on the top right of your Pushover home screen and probably starts with a u_  \n",
+    "PUSHOVER_TOKEN=_put the key when you click into your new application called Agents (or whatever) and probably starts with an a_\n",
+    "\n",
+    "Remember to save your `.env` file, and run `load_dotenv(override=True)` after saving, to set your environment variables.\n",
+    "\n",
+    "Finally, click \"Add Phone, Tablet or Desktop\" to install on your phone."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "import json\n",
+    "import os\n",
+    "import requests\n",
+    "from pypdf import PdfReader\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The usual start\n",
+    "\n",
+    "load_dotenv(override=True)\n",
+    "GEMINI_BASE_URL = \"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n",
+    "gemini = OpenAI(base_url=GEMINI_BASE_URL, api_key=google_api_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# For pushover\n",
+    "\n",
+    "pushover_user = os.getenv(\"PUSHOVER_USER\")\n",
+    "pushover_token = os.getenv(\"PUSHOVER_TOKEN\")\n",
+    "pushover_url = \"https://api.pushover.net/1/messages.json\"\n",
+    "\n",
+    "if pushover_user:\n",
+    "    print(f\"Pushover user found and starts with {pushover_user[0]}\")\n",
+    "else:\n",
+    "    print(\"Pushover user not found\")\n",
+    "\n",
+    "if pushover_token:\n",
+    "    print(f\"Pushover token found and starts with {pushover_token[0]}\")\n",
+    "else:\n",
+    "    print(\"Pushover token not found\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def push(message):\n",
+    "    print(f\"Push: {message}\")\n",
+    "    payload = {\"user\": pushover_user, \"token\": pushover_token, \"message\": message}\n",
+    "    requests.post(pushover_url, data=payload)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "push(\"HEY!!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def record_user_details(email, name=\"Name not provided\", notes=\"not provided\"):\n",
+    "    push(f\"Recording interest from {name} with email {email} and notes {notes}\")\n",
+    "    return {\"recorded\": \"ok\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def record_unknown_question(question):\n",
+    "    push(f\"Recording {question} asked that I couldn't answer\")\n",
+    "    return {\"recorded\": \"ok\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "record_user_details_json = {\n",
+    "    \"name\": \"record_user_details\",\n",
+    "    \"description\": \"Use this tool to record that a user is interested in being in touch and provided an email address\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"email\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The email address of this user\"\n",
+    "            },\n",
+    "            \"name\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The user's name, if they provided it\"\n",
+    "            }\n",
+    "            ,\n",
+    "            \"notes\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"Any additional information about the conversation that's worth recording to give context\"\n",
+    "            }\n",
+    "        },\n",
+    "        \"required\": [\"email\"],\n",
+    "        \"additionalProperties\": False\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "record_unknown_question_json = {\n",
+    "    \"name\": \"record_unknown_question\",\n",
+    "    \"description\": \"Always use this tool to record any question that couldn't be answered as you didn't know the answer\",\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "            \"question\": {\n",
+    "                \"type\": \"string\",\n",
+    "                \"description\": \"The question that couldn't be answered\"\n",
+    "            },\n",
+    "        },\n",
+    "        \"required\": [\"question\"],\n",
+    "        \"additionalProperties\": False\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = [{\"type\": \"function\", \"function\": record_user_details_json},\n",
+    "        {\"type\": \"function\", \"function\": record_unknown_question_json}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This function can take a list of tool calls, and run them. This is the IF statement!!\n",
+    "\n",
+    "def handle_tool_calls(tool_calls):\n",
+    "    results = []\n",
+    "    for tool_call in tool_calls:\n",
+    "        tool_name = tool_call.function.name\n",
+    "        arguments = json.loads(tool_call.function.arguments)\n",
+    "        print(f\"Tool called: {tool_name}\", flush=True)\n",
+    "\n",
+    "        # THE BIG IF STATEMENT!!!\n",
+    "\n",
+    "        if tool_name == \"record_user_details\":\n",
+    "            result = record_user_details(**arguments)\n",
+    "        elif tool_name == \"record_unknown_question\":\n",
+    "            result = record_unknown_question(**arguments)\n",
+    "\n",
+    "        results.append({\"role\": \"tool\",\"content\": json.dumps(result),\"tool_call_id\": tool_call.id})\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "globals()[\"record_unknown_question\"](\"this is a really hard question\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This is a more elegant way that avoids the IF statement.\n",
+    "\n",
+    "def handle_tool_calls(tool_calls):\n",
+    "    results = []\n",
+    "    for tool_call in tool_calls:\n",
+    "        tool_name = tool_call.function.name\n",
+    "        arguments = json.loads(tool_call.function.arguments)\n",
+    "        print(f\"Tool called: {tool_name}\", flush=True)\n",
+    "        tool = globals().get(tool_name)\n",
+    "        result = tool(**arguments) if tool else {}\n",
+    "        results.append({\"role\": \"tool\",\"content\": json.dumps(result),\"tool_call_id\": tool_call.id})\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reader = PdfReader(\"me/linkedin.pdf\")\n",
+    "linkedin = \"\"\n",
+    "for page in reader.pages:\n",
+    "    text = page.extract_text()\n",
+    "    if text:\n",
+    "        linkedin += text\n",
+    "\n",
+    "with open(\"me/summary.txt\", \"r\", encoding=\"utf-8\") as f:\n",
+    "    summary = f.read()\n",
+    "\n",
+    "name = \"Harsh Patidar\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = f\"You are acting as {name}. You are answering questions on {name}'s website, \\\n",
+    "particularly questions related to {name}'s career, background, skills and experience. \\\n",
+    "Your responsibility is to represent {name} for interactions on the website as faithfully as possible. \\\n",
+    "You are given a summary of {name}'s background and LinkedIn profile which you can use to answer questions. \\\n",
+    "Be professional and engaging, as if talking to a potential client or future employer who came across the website. \\\n",
+    "If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \\\n",
+    "If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. \"\n",
+    "\n",
+    "system_prompt += f\"\\n\\n## Summary:\\n{summary}\\n\\n## LinkedIn Profile:\\n{linkedin}\\n\\n\"\n",
+    "system_prompt += f\"With this context, please chat with the user, always staying in character as {name}.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = \"gemini-2.5-flash-preview-05-20\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from turtle import mode\n",
+    "\n",
+    "\n",
+    "def chat(message, history):\n",
+    "    messages = [{\"role\": \"system\", \"content\": system_prompt}] + history + [{\"role\": \"user\", \"content\": message}]\n",
+    "    done = False\n",
+    "    while not done:\n",
+    "\n",
+    "        # This is the call to the LLM - see that we pass in the tools json\n",
+    "\n",
+    "        response = gemini.chat.completions.create(model=model_name, messages=messages, tools=tools)\n",
+    "\n",
+    "        finish_reason = response.choices[0].finish_reason\n",
+    "        \n",
+    "        # If the LLM wants to call a tool, we do that!\n",
+    "         \n",
+    "        if finish_reason==\"tool_calls\":\n",
+    "            message = response.choices[0].message\n",
+    "            tool_calls = message.tool_calls\n",
+    "            results = handle_tool_calls(tool_calls)\n",
+    "            messages.append(message)\n",
+    "            messages.extend(results)\n",
+    "        else:\n",
+    "            done = True\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gr.ChatInterface(chat, type=\"messages\").launch()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## And now for deployment\n",
+    "\n",
+    "This code is in `app.py`\n",
+    "\n",
+    "We will deploy to HuggingFace Spaces.\n",
+    "\n",
+    "Before you start: remember to update the files in the \"me\" directory - your LinkedIn profile and summary.txt - so that it talks about you! Also change `self.name = \"Ed Donner\"` in `app.py`..  \n",
+    "\n",
+    "Also check that there's no README file within the 1_foundations directory. If there is one, please delete it. The deploy process creates a new README file in this directory for you.\n",
+    "\n",
+    "1. Visit https://huggingface.co and set up an account  \n",
+    "2. From the Avatar menu on the top right, choose Access Tokens. Choose \"Create New Token\". Give it WRITE permissions - it needs to have WRITE permissions! Keep a record of your new key.  \n",
+    "3. In the Terminal, run: `uv tool install 'huggingface_hub[cli]'` to install the HuggingFace tool, then `hf auth login --token YOUR_TOKEN_HERE`, like `hf auth login --token hf_xxxxxx`, to login at the command line with your key. Afterwards, run `hf auth whoami` to check you're logged in  \n",
+    "4. Take your new token and add it to your .env file: `HF_TOKEN=hf_xxx` for the future\n",
+    "5. From the 1_foundations folder, enter: `uv run gradio deploy` \n",
+    "6. Follow its instructions: name it \"career_conversation\", specify app.py, choose cpu-basic as the hardware, say Yes to needing to supply secrets, provide your openai api key, your pushover user and token, and say \"no\" to github actions.  \n",
+    "\n",
+    "Thank you Robert, James, Martins, Andras and Priya for these tips.  \n",
+    "Please read the next 2 sections - how to change your Secrets, and how to redeploy your Space (you may need to delete the README.md that gets created in this 1_foundations directory).\n",
+    "\n",
+    "#### More about these secrets:\n",
+    "\n",
+    "If you're confused by what's going on with these secrets: it just wants you to enter the key name and value for each of your secrets -- so you would enter:  \n",
+    "`OPENAI_API_KEY`  \n",
+    "Followed by:  \n",
+    "`sk-proj-...`  \n",
+    "\n",
+    "And if you don't want to set secrets this way, or something goes wrong with it, it's no problem - you can change your secrets later:  \n",
+    "1. Log in to HuggingFace website  \n",
+    "2. Go to your profile screen via the Avatar menu on the top right  \n",
+    "3. Select the Space you deployed  \n",
+    "4. Click on the Settings wheel on the top right  \n",
+    "5. You can scroll down to change your secrets (Variables and Secrets section), delete the space, etc.\n",
+    "\n",
+    "#### And now you should be deployed!\n",
+    "\n",
+    "If you want to completely replace everything and start again with your keys, you may need to delete the README.md that got created in this 1_foundations folder.\n",
+    "\n",
+    "Here is mine: https://huggingface.co/spaces/ed-donner/Career_Conversation\n",
+    "\n",
+    "I just got a push notification that a student asked me how they can become President of their country 😂😂\n",
+    "\n",
+    "For more information on deployment:\n",
+    "\n",
+    "https://www.gradio.app/guides/sharing-your-app#hosting-on-hf-spaces\n",
+    "\n",
+    "To delete your Space in the future:  \n",
+    "1. Log in to HuggingFace\n",
+    "2. From the Avatar menu, select your profile\n",
+    "3. Click on the Space itself and select the settings wheel on the top right\n",
+    "4. Scroll to the Delete section at the bottom\n",
+    "5. ALSO: delete the README file that Gradio may have created inside this 1_foundations folder (otherwise it won't ask you the questions the next time you do a gradio deploy)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">• First and foremost, deploy this for yourself! It's a real, valuable tool - the future resume..<br/>\n",
+    "            • Next, improve the resources - add better context about yourself. If you know RAG, then add a knowledge base about you.<br/>\n",
+    "            • Add in more tools! You could have a SQL database with common Q&A that the LLM could read and write from?<br/>\n",
+    "            • Bring in the Evaluator from the last lab, and add other Agentic patterns.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">Aside from the obvious (your career alter-ego) this has business applications in any situation where you need an AI assistant with domain expertise and an ability to interact with the real world.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_foundations_using_gemini/app.py

@@ -0,0 +1,136 @@
+from dotenv import load_dotenv
+from openai import OpenAI
+import json
+import os
+import requests
+from pypdf import PdfReader
+import gradio as gr
+
+
+load_dotenv(override=True)
+
+def push(text):
+    requests.post(
+        "https://api.pushover.net/1/messages.json",
+        data={
+            "token": os.getenv("PUSHOVER_TOKEN"),
+            "user": os.getenv("PUSHOVER_USER"),
+            "message": text,
+        }
+    )
+
+
+def record_user_details(email, name="Name not provided", notes="not provided"):
+    push(f"Recording {name} with email {email} and notes {notes}")
+    return {"recorded": "ok"}
+
+def record_unknown_question(question):
+    push(f"Recording {question}")
+    return {"recorded": "ok"}
+
+record_user_details_json = {
+    "name": "record_user_details",
+    "description": "Use this tool to record that a user is interested in being in touch and provided an email address",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "email": {
+                "type": "string",
+                "description": "The email address of this user"
+            },
+            "name": {
+                "type": "string",
+                "description": "The user's name, if they provided it"
+            }
+            ,
+            "notes": {
+                "type": "string",
+                "description": "Any additional information about the conversation that's worth recording to give context"
+            }
+        },
+        "required": ["email"],
+        "additionalProperties": False
+    }
+}
+
+record_unknown_question_json = {
+    "name": "record_unknown_question",
+    "description": "Always use this tool to record any question that couldn't be answered as you didn't know the answer",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "question": {
+                "type": "string",
+                "description": "The question that couldn't be answered"
+            },
+        },
+        "required": ["question"],
+        "additionalProperties": False
+    }
+}
+
+tools = [{"type": "function", "function": record_user_details_json},
+        {"type": "function", "function": record_unknown_question_json}]
+
+
+class Me:
+
+    def __init__(self):
+        self.GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta/openai/"
+        self.GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+        self.openai = OpenAI(base_url=self.GEMINI_BASE_URL, api_key=self.GOOGLE_API_KEY)
+        self.name = "Harsh Patidar"
+        reader = PdfReader("me/linkedin.pdf")
+        self.linkedin = ""
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                self.linkedin += text
+        with open("me/summary.txt", "r", encoding="utf-8") as f:
+            self.summary = f.read()
+
+
+    def handle_tool_call(self, tool_calls):
+        results = []
+        for tool_call in tool_calls:
+            tool_name = tool_call.function.name
+            arguments = json.loads(tool_call.function.arguments)
+            print(f"Tool called: {tool_name}", flush=True)
+            tool = globals().get(tool_name)
+            result = tool(**arguments) if tool else {}
+            results.append({"role": "tool","content": json.dumps(result),"tool_call_id": tool_call.id})
+        return results
+    
+    def system_prompt(self):
+        system_prompt = f"You are acting as {self.name}. You are answering questions on {self.name}'s website, \
+particularly questions related to {self.name}'s career, background, skills and experience. \
+Your responsibility is to represent {self.name} for interactions on the website as faithfully as possible. \
+You are given a summary of {self.name}'s background and LinkedIn profile which you can use to answer questions. \
+Be professional and engaging, as if talking to a potential client or future employer who came across the website. \
+If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \
+If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. "
+
+        system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n"
+        system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}."
+        return system_prompt
+    
+    def chat(self, message, history):
+        messages = [{"role": "system", "content": self.system_prompt()}] + history + [{"role": "user", "content": message}]
+        done = False
+        while not done:
+            response = self.openai.chat.completions.create(model="gemini-2.5-flash-preview-05-20", messages=messages, tools=tools)
+            if response.choices[0].finish_reason=="tool_calls":
+                message = response.choices[0].message
+                tool_calls = message.tool_calls
+                results = self.handle_tool_call(tool_calls)
+                messages.append(message)
+                messages.extend(results)
+            else:
+                done = True
+        return response.choices[0].message.content
+    
+
+if __name__ == "__main__":
+    me = Me()
+    gr.ChatInterface(me.chat, type="messages").launch()
+    

community_contributions/1_foundations_using_gemini/me/summary.txt

@@ -0,0 +1,11 @@
+Hey, I’m Harsh Patidar — a Data Engineer at ZS who loves building data systems that actually work — scalable, reliable, and smart enough to keep learning.
+I’ve spent the past few years turning raw, unstructured data into powerful systems that fuel analytics, automation, and AI-driven decisions.
+
+At ZS, I work in the R&D division, where I design and deploy containerized APIs, optimize data pipelines, and integrate machine learning models into real-world workflows. My toolkit revolves around Python, SQL, FastAPI, Docker, Airflow, and AWS, and I enjoy the process of connecting every piece of data infrastructure into something clean, efficient, and production-ready.
+
+Before this, I was part of Accenture’s Data Engineering & Governance team, helping large enterprises strengthen data reliability, validation, and compliance frameworks — experience that taught me the importance of structure, traceability, and precision.
+I also spent time as a Teaching Assistant at Coding Ninjas, mentoring over 200 students in Data Structures and Algorithms — something that shaped both my fundamentals and my patience.
+
+Outside of work, I’m someone who finds joy in photography, exploring tech startups, and deep research in finance and AI. I like observing how technology, creativity, and design come together — whether in a great photograph or a cleanly designed data pipeline.
+
+At my core, I’m driven by curiosity and the excitement of building something meaningful from scratch. I believe great work is built quietly, through learning, experimentation, and the discipline to keep improving — whether that’s a data system, a product, or even myself.

community_contributions/1_foundations_using_gemini/requirements.txt

@@ -0,0 +1,6 @@
+requests
+python-dotenv
+gradio
+pypdf
+openai
+openai-agents

community_contributions/1_lab1_DA.ipynb

@@ -0,0 +1,396 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv  import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-nano\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "from openai import OpenAI\n",
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "# And now we'll create an instance of the OpenAI class\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "\n",
+    "question1 = \"Please pick a business area that might be worth exploring for an Agentic AI opportunity.\"\n",
+    "messages1 = [{\"role\": \"user\", \"content\": question1}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "response1 = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages1\n",
+    ")\n",
+    "\n",
+    "question2 = \" Please present the pain-point in \"+response1.choices[0].message.content +\" industry - something challenging that might be ripe for an Agentic solution\"\n",
+    "messages2 = [{\"role\": \"user\", \"content\": question2}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "response2 = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages2\n",
+    ")\n",
+    "\n",
+    "question3 = \" Please presentpropose and Agentic AI solution for pain-point \"+response2.choices[0].message.content\n",
+    "messages3 = [{\"role\": \"user\", \"content\": question3}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "response3 = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages3\n",
+    ")\n",
+    "\n",
+    "Final_Answer = \" Please presentpropose and Agentic AI solution for pain-point \"+response2.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(Final_Answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_Hy.ipynb

@@ -0,0 +1,688 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI API Key exists and begins sk-proj-\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ChatCompletion(id='chatcmpl-C9oVaLh1gjzKH07zcVLaXQ4o4FDQ7', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='2 + 2 equals 4.', refusal=None, role='assistant', annotations=[], audio=None, function_call=None, tool_calls=None))], created=1756455142, model='gpt-4.1-nano-2025-04-14', object='chat.completion', service_tier='default', system_fingerprint='fp_c4c155951e', usage=CompletionUsage(completion_tokens=8, prompt_tokens=14, total_tokens=22, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=0, audio_tokens=0, reasoning_tokens=0, rejected_prediction_tokens=0), prompt_tokens_details=PromptTokensDetails(audio_tokens=0, cached_tokens=0)))\n",
+      "2 + 2 equals 4.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-nano\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "If three people can paint three walls in three hours, how many people are needed to paint 18 walls in six hours?\n"
+     ]
+    }
+   ],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Let's analyze the problem step-by-step:\n",
+      "\n",
+      "---\n",
+      "\n",
+      "**Given:**\n",
+      "\n",
+      "- 3 people can paint 3 walls in 3 hours.\n",
+      "\n",
+      "**Question:**\n",
+      "\n",
+      "- How many people are needed to paint 18 walls in 6 hours?\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 1: Find the rate of painting per person\n",
+      "\n",
+      "- Total walls painted: 3 walls\n",
+      "- Total people: 3 people\n",
+      "- Total time: 3 hours\n",
+      "\n",
+      "**Walls per person per hour:**\n",
+      "\n",
+      "First, find how many walls 3 people paint per hour:\n",
+      "\n",
+      "\\[\n",
+      "\\frac{3 \\text{ walls}}{3 \\text{ hours}} = 1 \\text{ wall per hour by 3 people}\n",
+      "\\]\n",
+      "\n",
+      "So, 3 people paint 1 wall per hour.\n",
+      "\n",
+      "Then, walls per person per hour:\n",
+      "\n",
+      "\\[\n",
+      "\\frac{1 \\text{ wall per hour}}{3 \\text{ people}} = \\frac{1}{3} \\text{ wall per person per hour}\n",
+      "\\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 2: Calculate total work needed\n",
+      "\n",
+      "You want to paint 18 walls in 6 hours.\n",
+      "\n",
+      "This means the rate of painting must be:\n",
+      "\n",
+      "\\[\n",
+      "\\frac{18 \\text{ walls}}{6 \\text{ hours}} = 3 \\text{ walls per hour}\n",
+      "\\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Step 3: Find how many people are needed for this rate\n",
+      "\n",
+      "Since each person paints \\(\\frac{1}{3}\\) wall per hour,\n",
+      "\n",
+      "\\[\n",
+      "\\text{Number of people} \\times \\frac{1}{3} = 3 \\text{ walls per hour}\n",
+      "\\]\n",
+      "\n",
+      "Multiply both sides by 3:\n",
+      "\n",
+      "\\[\n",
+      "\\text{Number of people} = 3 \\times 3 = 9\n",
+      "\\]\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### **Answer:**\n",
+      "\n",
+      "\\[\n",
+      "\\boxed{9}\n",
+      "\\]\n",
+      "\n",
+      "You need **9 people** to paint 18 walls in 6 hours.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Let's analyze the problem step-by-step:\n",
+       "\n",
+       "---\n",
+       "\n",
+       "**Given:**\n",
+       "\n",
+       "- 3 people can paint 3 walls in 3 hours.\n",
+       "\n",
+       "**Question:**\n",
+       "\n",
+       "- How many people are needed to paint 18 walls in 6 hours?\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 1: Find the rate of painting per person\n",
+       "\n",
+       "- Total walls painted: 3 walls\n",
+       "- Total people: 3 people\n",
+       "- Total time: 3 hours\n",
+       "\n",
+       "**Walls per person per hour:**\n",
+       "\n",
+       "First, find how many walls 3 people paint per hour:\n",
+       "\n",
+       "\\[\n",
+       "\\frac{3 \\text{ walls}}{3 \\text{ hours}} = 1 \\text{ wall per hour by 3 people}\n",
+       "\\]\n",
+       "\n",
+       "So, 3 people paint 1 wall per hour.\n",
+       "\n",
+       "Then, walls per person per hour:\n",
+       "\n",
+       "\\[\n",
+       "\\frac{1 \\text{ wall per hour}}{3 \\text{ people}} = \\frac{1}{3} \\text{ wall per person per hour}\n",
+       "\\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 2: Calculate total work needed\n",
+       "\n",
+       "You want to paint 18 walls in 6 hours.\n",
+       "\n",
+       "This means the rate of painting must be:\n",
+       "\n",
+       "\\[\n",
+       "\\frac{18 \\text{ walls}}{6 \\text{ hours}} = 3 \\text{ walls per hour}\n",
+       "\\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### Step 3: Find how many people are needed for this rate\n",
+       "\n",
+       "Since each person paints \\(\\frac{1}{3}\\) wall per hour,\n",
+       "\n",
+       "\\[\n",
+       "\\text{Number of people} \\times \\frac{1}{3} = 3 \\text{ walls per hour}\n",
+       "\\]\n",
+       "\n",
+       "Multiply both sides by 3:\n",
+       "\n",
+       "\\[\n",
+       "\\text{Number of people} = 3 \\times 3 = 9\n",
+       "\\]\n",
+       "\n",
+       "---\n",
+       "\n",
+       "### **Answer:**\n",
+       "\n",
+       "\\[\n",
+       "\\boxed{9}\n",
+       "\\]\n",
+       "\n",
+       "You need **9 people** to paint 18 walls in 6 hours."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Certainly! Building on your outlined pain-point and the high-level Agentic AI functionalities, here’s a detailed proposal for an **Agentic AI solution** designed to tackle fragmented patient data and enable real-time, holistic health management.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "# Agentic AI Solution Proposal: **HealthSynth AI**\n",
+       "\n",
+       "### Overview  \n",
+       "**HealthSynth AI** is an autonomous health management agent that continuously synthesizes fragmented patient data from multiple sources to provide a real-time, unified, and actionable health profile for patients and their care teams. It acts as a 24/7 health assistant, proactive coordinator, and personalized medical advisor.\n",
+       "\n",
+       "---\n",
+       "\n",
+       "## Key Features & Capabilities\n",
+       "\n",
+       "### 1. **Autonomous Data Aggregation & Normalization**  \n",
+       "- Uses API integrations, secure data exchanges (FHIR, HL7 standards), and device SDKs to continuously fetch data from:  \n",
+       "  - EHR systems across different providers  \n",
+       "  - Wearable and home medical devices (heart rate, glucose monitors, BP cuffs)  \n",
+       "  - Pharmacy records and prescription databases  \n",
+       "  - Lab results portals  \n",
+       "  - Insurance claims and coverage data  \n",
+       "- Applies intelligent data cleaning, deduplication, and semantic normalization to unify heterogeneous data formats into a consistent patient health graph.\n",
+       "\n",
+       "### 2. **Real-Time Multimodal Health Analytics Engine**  \n",
+       "- Employs advanced ML and deep learning models to detect:  \n",
+       "  - Emerging risk patterns (e.g., early signs of infection, deterioration of chronic conditions)  \n",
+       "  - Anomalies (missed medications, unusual vital sign changes)  \n",
+       "  - Compliance gaps (lifestyle, medication adherence)  \n",
+       "- Continuously updates predictive health trajectories personalized to each patient’s condition and history.\n",
+       "\n",
+       "### 3. **Proactive Action & Recommendation System**  \n",
+       "- Generates context-aware, evidence-based alerts and recommendations such as:  \n",
+       "  - Medication reminders or dosage adjustments flagged in consultation with prescribing physicians  \n",
+       "  - Suggestions for scheduling lab tests or specialist visits timely before symptoms worsen  \n",
+       "  - Lifestyle coaching tips adapted using patient preferences and progress  \n",
+       "- Classes recommendations into urgency tiers (info, caution, immediate action) and routes notifications appropriately.\n",
+       "\n",
+       "### 4. **Automated Care Coordination & Workflow Integration**  \n",
+       "- Interacts programmatically with provider scheduling systems, telemedicine platforms, pharmacies, and insurance portals to:  \n",
+       "  - Automatically request appointment reschedules or referrals based on patient status  \n",
+       "  - Notify involved healthcare professionals about critical health events or lab results  \n",
+       "  - Facilitate prescription renewals or modifications with minimal human intervention  \n",
+       "- Maintains secure, auditable communication logs ensuring compliance (HIPAA, GDPR).\n",
+       "\n",
+       "### 5. **Patient-Centric Digital Health Companion**  \n",
+       "- Provides patients with an intuitive mobile/web app featuring:  \n",
+       "  - A dynamic health dashboard summarizing key metrics, risks, and recent activities in plain language  \n",
+       "  - Intelligent daily check-ins and symptom trackers powered by conversational AI  \n",
+       "  - Adaptive educational content tailored to health literacy levels and language preferences  \n",
+       "  - Privacy controls empowering patients to manage data sharing settings\n",
+       "\n",
+       "---\n",
+       "\n",
+       "## Technical Architecture (High-Level)\n",
+       "\n",
+       "- **Data Ingestion Layer:** Connectors for EHRs, wearables, pharmacies, labs  \n",
+       "- **Data Lake & Processing:** Cloud-native secure storage with HIPAA-compliant encryption  \n",
+       "- **Knowledge Graph:** Patient-centric semantic graph linking clinical concepts, timelines, interventions  \n",
+       "- **Analytics & ML Models:** Ensemble predictive models incorporating temporal health data, risk scoring, anomaly detection  \n",
+       "- **Agentic Orchestrator:** Rule-based and reinforcement learning-driven workflow engine enabling autonomous decision-making and stakeholder communications  \n",
+       "- **Frontend Interfaces:** Responsive patient app, provider portals, API access for system integration\n",
+       "\n",
+       "---\n",
+       "\n",
+       "## Potential Challenges & Mitigations\n",
+       "\n",
+       "| Challenge | Mitigation Strategy |\n",
+       "|-----------|---------------------|\n",
+       "| Data privacy & regulatory compliance | Built-in privacy-by-design, end-to-end encryption, rigorous consent management, audit trails |\n",
+       "| Data interoperability & standardization | Utilize open standards (FHIR, DICOM), NLP for unstructured data extraction |\n",
+       "| Model explainability | Implement interpretable ML techniques and transparent reasoning for clinicians |\n",
+       "| Patient engagement sustainability | Gamification, behavior science-driven personalized nudges |\n",
+       "| Integration complexity across healthcare IT systems | Modular adaptors/plugins, partnerships with major EHR vendors |\n",
+       "\n",
+       "---\n",
+       "\n",
+       "## Impact & Benefits\n",
+       "\n",
+       "- **For Patients:** Reduced health risks, increased empowerment, improved treatment adherence, and personal convenience  \n",
+       "- **For Providers:** Enhanced clinical decision support, reduced administrative burden, timely interventions  \n",
+       "- **For Payers:** Lowered costs via preventive care and reduced hospital readmissions\n",
+       "\n",
+       "---\n",
+       "\n",
+       "Would you like me to help you design detailed user journeys, develop specific ML model architectures, or draft an implementation roadmap for **HealthSynth AI**?"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"I want you to pick a business area that might be worth exploring for an Agentic AI opportunity.\"}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.choices[0].message.content\n",
+    "\n",
+    "# print(business_idea)\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": f\"Please propose a pain-point in the {business_idea} industry.\"}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "pain_point = response.choices[0].message.content\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": f\"Please propose an Agentic AI solution to the pain-point: {pain_point}.\"}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "agentic_solution = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(agentic_solution))\n",
+    "\n",
+    "# And repeat! In the next message, include the business idea within the message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_Mudassar.ipynb

@@ -0,0 +1,260 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# First Agentic AI workflow with OPENAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/muhammad-mudassar-a65645192/"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import re\n",
+    "from openai import OpenAI\n",
+    "from dotenv import load_dotenv\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai_api_key=os.getenv(\"OPENAI_API_KEY\")\n",
+    "if openai_api_key:\n",
+    "    print(f\"openai api key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the gui\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Workflow with OPENAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai=OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message = [{'role':'user','content':\"what is 2+3?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "print(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "message=[{'role':'user','content':question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response=openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "question=response.choices[0].message.content\n",
+    "print(f\"Answer: {question}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message=[{'role':'user','content':question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response=openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "answer = response.choices[0].message.content\n",
+    "print(f\"Answer: {answer}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# convert \\[ ... \\] to $$ ... $$, to properly render Latex\n",
+    "converted_answer = re.sub(r'\\\\[\\[\\]]', '$$', answer)\n",
+    "display(Markdown(converted_answer))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exercise"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message = [{'role':'user','content':\"give me a business area related to ecommerce that might be worth exploring for a agentic opportunity.\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "business_area = response.choices[0].message.content\n",
+    "business_area"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message = business_area + \"present a pain-point in that industry - something challenging that might be ripe for an agentic solutions.\"\n",
+    "message"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message = [{'role': 'user', 'content': message}]\n",
+    "response = openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "question=response.choices[0].message.content\n",
+    "question"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "message=[{'role':'user','content':question}]\n",
+    "response=openai.chat.completions.create(model=\"gpt-4o-mini\",messages=message)\n",
+    "answer=response.choices[0].message.content\n",
+    "print(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display(Markdown(answer))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_Thanh.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the keys\n",
+    "import google.generativeai as genai\n",
+    "import os\n",
+    "genai.configure(api_key=os.getenv('GOOGLE_API_KEY'))\n",
+    "model = genai.GenerativeModel(model_name=\"gemini-1.5-flash\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar Gemini GenAI format\n",
+    "\n",
+    "response = model.generate_content([\"2+2=?\"])\n",
+    "response.text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "\n",
+    "response = model.generate_content([question])\n",
+    "print(response.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(response.text))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Something here\"}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response =\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.\n",
+    "\n",
+    "# And repeat!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llm_projects",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_cm.ipynb

@@ -0,0 +1,305 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Treat these labs as a resource</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates to the code regularly. When people ask questions or have problems, I incorporate it in the code, adding more examples or improved commentary. As a result, you'll notice that the code below isn't identical to the videos. Everything from the videos is here; but in addition, I've added more steps and better explanations. Consider this like an interactive book that accompanies the lectures.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Run `uv add google-genai` to install the Google Gemini library. (If you had started your environment before running this command, you will need to restart your environment in the Jupyter notebook.)\n",
+    "2. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "3. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "4. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. From the Cursor menu, choose Settings >> VSCode Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the keys\n",
+    "\n",
+    "import os\n",
+    "gemini_api_key = os.getenv('GEMINI_API_KEY')\n",
+    "\n",
+    "if gemini_api_key:\n",
+    "    print(f\"Gemini API Key exists and begins {gemini_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"Gemini API Key not set - please head to the troubleshooting guide in the guides folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting guide\n",
+    "\n",
+    "from google import genai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the Gemini GenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder!\n",
+    "# If you get a NameError - head over to the guides folder to learn about NameErrors\n",
+    "\n",
+    "client = genai.Client(api_key=gemini_api_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar Gemini GenAI format\n",
+    "\n",
+    "messages = [\"What is 2+2?\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=messages\n",
+    ")\n",
+    "\n",
+    "print(response.text)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# Lets no create a challenging question\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "\n",
+    "# Ask the the model\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=question\n",
+    ")\n",
+    "\n",
+    "question = response.text\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask the models generated question to the model\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=question\n",
+    ")\n",
+    "\n",
+    "# Extract the answer from the response\n",
+    "answer = response.text\n",
+    "\n",
+    "# Debug log the answer\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "# Nicely format the answer using Markdown\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "\n",
+    "messages = [\"Something here\"]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response =\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.\n",
+    "\n",
+    "# And repeat!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_gemini.ipynb

@@ -0,0 +1,305 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Treat these labs as a resource</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates to the code regularly. When people ask questions or have problems, I incorporate it in the code, adding more examples or improved commentary. As a result, you'll notice that the code below isn't identical to the videos. Everything from the videos is here; but in addition, I've added more steps and better explanations. Consider this like an interactive book that accompanies the lectures.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Run `uv add google-genai` to install the Google Gemini library. (If you had started your environment before running this command, you will need to restart your environment in the Jupyter notebook.)\n",
+    "2. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "3. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "4. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. From the Cursor menu, choose Settings >> VSCode Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the keys\n",
+    "\n",
+    "import os\n",
+    "gemini_api_key = os.getenv('GEMINI_API_KEY')\n",
+    "\n",
+    "if gemini_api_key:\n",
+    "    print(f\"Gemini API Key exists and begins {gemini_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"Gemini API Key not set - please head to the troubleshooting guide in the guides folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting guide\n",
+    "\n",
+    "from google import genai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the Gemini GenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder!\n",
+    "# If you get a NameError - head over to the guides folder to learn about NameErrors\n",
+    "\n",
+    "client = genai.Client(api_key=gemini_api_key)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar Gemini GenAI format\n",
+    "\n",
+    "messages = [\"What is 2+2?\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=messages\n",
+    ")\n",
+    "\n",
+    "print(response.text)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# Lets no create a challenging question\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "\n",
+    "# Ask the the model\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=question\n",
+    ")\n",
+    "\n",
+    "question = response.text\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask the models generated question to the model\n",
+    "response = client.models.generate_content(\n",
+    "    model=\"gemini-2.0-flash\", contents=question\n",
+    ")\n",
+    "\n",
+    "# Extract the answer from the response\n",
+    "answer = response.text\n",
+    "\n",
+    "# Debug log the answer\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "# Nicely format the answer using Markdown\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "\n",
+    "messages = [\"Something here\"]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response =\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.\n",
+    "\n",
+    "# And repeat!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_groq.ipynb

@@ -0,0 +1,262 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Implementing Notebook 1 using various LLMs via Groq"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI(\n",
+    "    base_url=\"https://api.groq.com/openai/v1\",\n",
+    "    api_key=groq_api_key\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# openai/gpt-oss-120b\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"openai/gpt-oss-120b\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# moonshotai/kimi-k2-instruct\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"moonshotai/kimi-k2-instruct\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask meta-llama/llama-guard-4-12b\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"llama-3.1-8b-instant\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(question))\n",
+    "display(Markdown(answer))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Pick a business area that is worth exploring for a Gen-Z audience, that can be an agentic-ai opportunity. \\\n",
+    "             Somehwere where the concept of agentisation can be applied commerically. Respond only with the business idea.\"}]\n",
+    "\n",
+    "# Then make the first call: \n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = \"qwen/qwen3-32b\",\n",
+    "    messages = messages\n",
+    ")\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.choices[0].message.content\n",
+    "print(business_idea)\n",
+    "\n",
+    "# And repeat! In the next message, include the business idea within the message\n",
+    "\n",
+    "user_prompt_pain_point = f\"What is the pain point of the Gen-Z audience in the business area of {business_idea}?, that can be solved by an agentic-ai solution? Give a brief answer\"\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = \"gemma2-9b-it\",\n",
+    "    messages = [{\"role\": \"user\", \"content\": user_prompt_pain_point}]\n",
+    ")\n",
+    "\n",
+    "pain_point = response.choices[0].message.content\n",
+    "print(pain_point)\n",
+    "\n",
+    "user_prompt_solution = f\"What is the solution to the pain point {pain_point} of the Gen-Z audience in the business area of {business_idea}?, that can be solved by an agentic-ai solution? Provide a step-by-step breakdown\"\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model = \"deepseek-r1-distill-llama-70b\",\n",
+    "    messages = [{\"role\": \"user\", \"content\": user_prompt_solution}]\n",
+    ")\n",
+    "\n",
+    "business_solution = response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display(Markdown(business_solution))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_groq_llama.ipynb

@@ -0,0 +1,296 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# First Agentic AI workflow with Groq and Llama-3.3 LLM(Free of cost) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import\n",
+    "from dotenv import load_dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the Groq API key\n",
+    "\n",
+    "import os\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"GROQ API Key exists and begins {groq_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"GROQ API Key not set\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting guide\n",
+    "\n",
+    "from groq import Groq"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a Groq instance\n",
+    "groq = Groq()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar Groq format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it!\n",
+    "\n",
+    "response = groq.chat.completions.create(model='llama-3.3-70b-versatile', messages=messages)\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ask it\n",
+    "response = groq.chat.completions.create(\n",
+    "    model=\"llama-3.3-70b-versatile\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = groq.chat.completions.create(\n",
+    "    model=\"llama-3.3-70b-versatile\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Give me a business area that might be ripe for an Agentic AI solution.\"}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response = groq.chat.completions.create(model='llama-3.3-70b-versatile', messages=messages)\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.choices[0].message.content\n",
+    "\n",
+    "\n",
+    "# And repeat!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "display(Markdown(business_idea))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Update the message with the business idea from previous step\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is the pain point in the business area of \" + business_idea + \"?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make the second call\n",
+    "response = groq.chat.completions.create(model='llama-3.3-70b-versatile', messages=messages)\n",
+    "# Read the pain point\n",
+    "pain_point = response.choices[0].message.content\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display(Markdown(pain_point))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make the third call\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is the Agentic AI solution for the pain point of \" + pain_point + \"?\"}]\n",
+    "response = groq.chat.completions.create(model='llama-3.3-70b-versatile', messages=messages)\n",
+    "# Read the agentic solution\n",
+    "agentic_solution = response.choices[0].message.content\n",
+    "display(Markdown(agentic_solution))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_marstipton_mac.ipynb

@@ -0,0 +1,411 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 1: Define the conversation\n",
+    "messages = [\n",
+    "    {\"role\": \"system\", \"content\": \"You are an expert in agentic AI business ideation.\"}\n",
+    "]\n",
+    "\n",
+    "# Step 2: Ask the first question\n",
+    "area_prompt = (\n",
+    "    \"Pick a business area within Singapore startups as of Q4 2025 \"\n",
+    "    \"that might be worth exploring for an Agentic AI opportunity. \"\n",
+    "    \"Explain in simple language (for a 15-year-old) and cite resources briefly.\"\n",
+    ")\n",
+    "messages.append({\"role\": \"user\", \"content\": area_prompt})\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "area = response.choices[0].message.content\n",
+    "display(Markdown(area))\n",
+    "\n",
+    "# Add model response to context\n",
+    "messages.append({\"role\": \"assistant\", \"content\": area})\n",
+    "\n",
+    "# Step 3: Ask for a pain point\n",
+    "painpoint_prompt = (\n",
+    "    \"Based on your previous response, pick a recurring pain point in that area \"\n",
+    "    \"that is ripe for an Agentic AI solution.\"\n",
+    ")\n",
+    "messages.append({\"role\": \"user\", \"content\": painpoint_prompt})\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "painpoint = response.choices[0].message.content\n",
+    "display(Markdown(painpoint))\n",
+    "\n",
+    "# Add model response to context\n",
+    "messages.append({\"role\": \"assistant\", \"content\": painpoint})\n",
+    "\n",
+    "# Step 4: Propose a business idea\n",
+    "business_idea_prompt = (\n",
+    "    \"Propose an Agentic AI solution addressing the pain point above. \"\n",
+    "    \"Solution should have low overhead, be secure, and offer 80% free functionality, \"\n",
+    "    \"with full access for SGD 0.99/month per user or SGD 15/org (max 30 users).\"\n",
+    ")\n",
+    "messages.append({\"role\": \"user\", \"content\": business_idea_prompt})\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "business_idea = response.choices[0].message.content\n",
+    "display(Markdown(business_idea))\n",
+    "\n",
+    "# Add to conversation (for future iterations)\n",
+    "#messages.append({\"role\": \"assistant\", \"content\": business_idea})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_moneek.ipynb

@@ -0,0 +1,407 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you read the <a href=\"../README.md\">README</a>? Many common questions are answered here!<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import. If you get an Import Error, double check that your Kernel is correct..\n",
+    "\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "# If this returns false, see the next cell!\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Wait, did that just output `False`??\n",
+    "\n",
+    "If so, the most common reason is that you didn't save your `.env` file after adding the key! Be sure to have saved.\n",
+    "\n",
+    "Also, make sure the `.env` file is named precisely `.env` and is in the project root directory (`agents`)\n",
+    "\n",
+    "By the way, your `.env` file should have a stop symbol next to it in Cursor on the left, and that's actually a good thing: that's Cursor saying to you, \"hey, I realize this is a file filled with secret information, and I'm not going to send it to an external AI to suggest changes, because your keys should not be shown to anyone else.\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Final reminders</h2>\n",
+    "            <span style=\"color:#ff7800;\">1. If you're not confident about Environment Variables or Web Endpoints / APIs, please read Topics 3 and 5 in this <a href=\"../guides/04_technical_foundations.ipynb\">technical foundations guide</a>.<br/>\n",
+    "            2. If you want to use AIs other than OpenAI, like Gemini, DeepSeek or Ollama (free), please see the first section in this <a href=\"../guides/09_ai_apis_and_ollama.ipynb\">AI APIs guide</a>.<br/>\n",
+    "            3. If you ever get a Name Error in Python, you can always fix it immediately; see the last section of this <a href=\"../guides/06_python_foundations.ipynb\">Python Foundations guide</a> and follow both tutorials and exercises.<br/>\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the key - if you're not using OpenAI, check whichever key you're using! Ollama doesn't need a key.\n",
+    "\n",
+    "import os\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set - please head to the troubleshooting guide in the setup folder\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - the all important import statement\n",
+    "# If you get an import error - head over to troubleshooting in the Setup folder\n",
+    "# Even for other LLM providers like Gemini, you still use this OpenAI import - see Guide 9 for why\n",
+    "\n",
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now we'll create an instance of the OpenAI class\n",
+    "# If you're not sure what it means to create an instance of a class - head over to the guides folder (guide 6)!\n",
+    "# If you get a NameError - head over to the guides folder (guide 6)to learn about NameErrors - always instantly fixable\n",
+    "# If you're not using OpenAI, you just need to slightly modify this - precise instructions are in the AI APIs guide (guide 9)\n",
+    "\n",
+    "openai = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a list of messages in the familiar OpenAI format\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now call it! Any problems, head to the troubleshooting guide\n",
+    "# This uses GPT 4.1 nano, the incredibly cheap model\n",
+    "# The APIs guide (guide 9) has exact instructions for using even cheaper or free alternatives to OpenAI\n",
+    "# If you get a NameError, head to the guides folder (guide 6) to learn about NameErrors - always instantly fixable\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-nano\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "print(response.choices[0].message.content)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ask it - this uses GPT 4.1 mini, still cheap but more powerful than nano\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution. <br/>\n",
+    "            We will cover this at up-coming labs, so don't worry if you're unsure.. just give it a try!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "question = \"Pick a business area that may have agentic AI opportunities\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.choices[0].message.content\n",
+    "print(business_idea)\n",
+    "\n",
+    "# And repeat! In the next message, include the business idea within the message"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": question + \"\\n\\n\" + business_idea},\n",
+    "            {\"role\": \"assistant\", \"content\": \"What is the pain point in this industry?\" }]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "pain_point = response.choices[0].message.content\n",
+    "print(pain_point)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": question + \"\\n\\n\" + business_idea + \"\\n\\n\" + pain_point},   \n",
+    "            {\"role\": \"assistant\", \"content\": \"What is the Agentic AI solution?\"}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4.1-mini\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "agentic_solution = response.choices[0].message.content\n",
+    "print(agentic_solution)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab1_open_router.ipynb

@@ -0,0 +1,323 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Welcome to the start of your adventure in Agentic AI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Are you ready for action??</h2>\n",
+    "            <span style=\"color:#ff7800;\">Have you completed all the setup steps in the <a href=\"../setup/\">setup</a> folder?<br/>\n",
+    "            Have you checked out the guides in the <a href=\"../guides/01_intro.ipynb\">guides</a> folder?<br/>\n",
+    "            Well in that case, you're ready!!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/tools.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">This code is a live resource - keep an eye out for my updates</h2>\n",
+    "            <span style=\"color:#00bfff;\">I push updates regularly. As people ask questions or have problems, I add more examples and improve explanations. As a result, the code below might not be identical to the videos, as I've added more steps and better comments. Consider this like an interactive book that accompanies the lectures.<br/><br/>\n",
+    "            I try to send emails regularly with important updates related to the course. You can find this in the 'Announcements' section of Udemy in the left sidebar. You can also choose to receive my emails via your Notification Settings in Udemy. I'm respectful of your inbox and always try to add value with my emails!\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### And please do remember to contact me if I can help\n",
+    "\n",
+    "And I love to connect: https://www.linkedin.com/in/eddonner/\n",
+    "\n",
+    "\n",
+    "### New to Notebooks like this one? Head over to the guides folder!\n",
+    "\n",
+    "Just to check you've already added the Python and Jupyter extensions to Cursor, if not already installed:\n",
+    "- Open extensions (View >> extensions)\n",
+    "- Search for python, and when the results show, click on the ms-python one, and Install it if not already installed\n",
+    "- Search for jupyter, and when the results show, click on the Microsoft one, and Install it if not already installed  \n",
+    "Then View >> Explorer to bring back the File Explorer.\n",
+    "\n",
+    "And then:\n",
+    "1. Click where it says \"Select Kernel\" near the top right, and select the option called `.venv (Python 3.12.9)` or similar, which should be the first choice or the most prominent choice. You may need to choose \"Python Environments\" first.\n",
+    "2. Click in each \"cell\" below, starting with the cell immediately below this text, and press Shift+Enter to run\n",
+    "3. Enjoy!\n",
+    "\n",
+    "After you click \"Select Kernel\", if there is no option like `.venv (Python 3.12.9)` then please do the following:  \n",
+    "1. On Mac: From the Cursor menu, choose Settings >> VS Code Settings (NOTE: be sure to select `VSCode Settings` not `Cursor Settings`);  \n",
+    "On Windows PC: From the File menu, choose Preferences >> VS Code Settings(NOTE: be sure to select `VSCode Settings` not `Cursor Settings`)  \n",
+    "2. In the Settings search bar, type \"venv\"  \n",
+    "3. In the field \"Path to folder with a list of Virtual Environments\" put the path to the project root, like C:\\Users\\username\\projects\\agents (on a Windows PC) or /Users/username/projects/agents (on Mac or Linux).  \n",
+    "And then try again.\n",
+    "\n",
+    "Having problems with missing Python versions in that list? Have you ever used Anaconda before? It might be interferring. Quit Cursor, bring up a new command line, and make sure that your Anaconda environment is deactivated:    \n",
+    "`conda deactivate`  \n",
+    "And if you still have any problems with conda and python versions, it's possible that you will need to run this too:  \n",
+    "`conda config --set auto_activate_base false`  \n",
+    "and then from within the Agents directory, you should be able to run `uv python list` and see the Python 3.12 version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First let's do an import\n",
+    "from dotenv import load_dotenv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Next it's time to load the API keys into environment variables\n",
+    "\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the keys\n",
+    "\n",
+    "import os\n",
+    "open_router_api_key = os.getenv('OPEN_ROUTER_API_KEY')\n",
+    "\n",
+    "if open_router_api_key:\n",
+    "    print(f\"Open router API Key exists and begins {open_router_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"Open router API Key not set - please head to the troubleshooting guide in the setup folder\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openai import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize the client to point at OpenRouter instead of OpenAI\n",
+    "# You can use the exact same OpenAI Python package—just swap the base_url!\n",
+    "client = OpenAI(\n",
+    "    base_url=\"https://openrouter.ai/api/v1\",\n",
+    "    api_key=open_router_api_key\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": \"What is 2+2?\"}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client = OpenAI(\n",
+    "    base_url=\"https://openrouter.ai/api/v1\",\n",
+    "    api_key=open_router_api_key\n",
+    ")\n",
+    "\n",
+    "resp = client.chat.completions.create(\n",
+    "    # Select a model from https://openrouter.ai/models and provide the model name here\n",
+    "    model=\"meta-llama/llama-3.3-8b-instruct:free\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "print(resp.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# And now - let's ask for a question:\n",
+    "\n",
+    "question = \"Please propose a hard, challenging question to assess someone's IQ. Respond only with the question.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = client.chat.completions.create(\n",
+    "    model=\"meta-llama/llama-3.3-8b-instruct:free\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "print(question)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# form a new messages list\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask it again\n",
+    "\n",
+    "response = client.chat.completions.create(\n",
+    "    model=\"meta-llama/llama-3.3-8b-instruct:free\",\n",
+    "    messages=messages\n",
+    ")\n",
+    "\n",
+    "answer = response.choices[0].message.content\n",
+    "print(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import Markdown, display\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Congratulations!\n",
+    "\n",
+    "That was a small, simple step in the direction of Agentic AI, with your new environment!\n",
+    "\n",
+    "Next time things get more interesting..."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Now try this commercial application:<br/>\n",
+    "            First ask the LLM to pick a business area that might be worth exploring for an Agentic AI opportunity.<br/>\n",
+    "            Then ask the LLM to present a pain-point in that industry - something challenging that might be ripe for an Agentic solution.<br/>\n",
+    "            Finally have 3 third LLM call propose the Agentic AI solution.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First create the messages:\n",
+    "\n",
+    "\n",
+    "messages = [\"Something here\"]\n",
+    "\n",
+    "# Then make the first call:\n",
+    "\n",
+    "response =\n",
+    "\n",
+    "# Then read the business idea:\n",
+    "\n",
+    "business_idea = response.\n",
+    "\n",
+    "# And repeat!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab2_Kaushik_Parallelization.ipynb

@@ -0,0 +1,355 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from IPython.display import Markdown"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Refresh dot env"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "open_api_key = os.getenv(\"OPENAI_API_KEY\")\n",
+    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create initial query to get challange reccomendation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = 'Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. '\n",
+    "query += 'Answer only with the question, no explanation.'\n",
+    "\n",
+    "messages = [{'role':'user', 'content':query}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Call openai gpt-4o-mini "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    messages=messages,\n",
+    "    model='gpt-4o-mini'\n",
+    ")\n",
+    "\n",
+    "challange = response.choices[0].message.content\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(challange)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create messages with the challange query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{'role':'user', 'content':challange}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from threading import Thread"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def gpt_mini_processor():\n",
+    "    modleName = 'gpt-4o-mini'\n",
+    "    competitors.append(modleName)\n",
+    "    response_gpt = openai.chat.completions.create(\n",
+    "        messages=messages,\n",
+    "        model=modleName\n",
+    "    )\n",
+    "    answers.append(response_gpt.choices[0].message.content)\n",
+    "\n",
+    "def gemini_processor():\n",
+    "    gemini = OpenAI(api_key=google_api_key, base_url='https://generativelanguage.googleapis.com/v1beta/openai/')\n",
+    "    modleName = 'gemini-2.0-flash'\n",
+    "    competitors.append(modleName)\n",
+    "    response_gemini = gemini.chat.completions.create(\n",
+    "        messages=messages,\n",
+    "        model=modleName\n",
+    "    )\n",
+    "    answers.append(response_gemini.choices[0].message.content)\n",
+    "\n",
+    "def llama_processor():\n",
+    "    ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "    modleName = 'llama3.2'\n",
+    "    competitors.append(modleName)\n",
+    "    response_llama = ollama.chat.completions.create(\n",
+    "        messages=messages,\n",
+    "        model=modleName\n",
+    "    )\n",
+    "    answers.append(response_llama.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Paraller execution of LLM calls"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "thread1 = Thread(target=gpt_mini_processor)\n",
+    "thread2 = Thread(target=gemini_processor)\n",
+    "thread3 = Thread(target=llama_processor)\n",
+    "\n",
+    "thread1.start()\n",
+    "thread2.start()\n",
+    "thread3.start()\n",
+    "\n",
+    "thread1.join()\n",
+    "thread2.join()\n",
+    "thread3.join()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(competitors)\n",
+    "print(answers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f'Competitor:{competitor}\\n\\n{answer}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "together = ''\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f'# Response from competitor {index + 1}\\n\\n'\n",
+    "    together += answer + '\\n\\n'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Prompt to judge the LLM results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "to_judge = f'''You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{challange}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n",
+    "\n",
+    "'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "to_judge_message = [{'role':'user', 'content':to_judge}]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Execute o3-mini to analyze the LLM results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    messages=to_judge_message,\n",
+    "    model='o3-mini'\n",
+    ")\n",
+    "result = response.choices[0].message.content\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results_dict = json.loads(result)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_lab2_Routing_Workflow.ipynb

@@ -0,0 +1,514 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Judging and Routing — Optimizing Resource Usage by Evaluating Problem Complexity"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In the original Lab 2, we explored the **Orchestrator–Worker pattern**, where a planner sent the same question to multiple agents, and a judge assessed their responses to evaluate agent intelligence.\n",
+    "\n",
+    "In this notebook, we extend that design by adding multiple judges and a routing component to optimize model usage based on task complexity. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports and Environment Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "if openai_api_key and google_api_key and deepseek_api_key:\n",
+    "    print(\"All keys were loaded successfully\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2\n",
+    "!ollama pull mistral"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Creating Models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The notebook uses instances of GPT, Gemini and DeepSeek APIs, along with two local models served via Ollama: ```llama3.2```  and ```mistral```."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_specs = {\n",
+    "    \"gpt-4o-mini\" : None,\n",
+    "    \"gemini-2.0-flash\": {\n",
+    "        \"api_key\" : google_api_key,\n",
+    "        \"url\" : \"https://generativelanguage.googleapis.com/v1beta/openai/\"\n",
+    "    },\n",
+    "    \"deepseek-chat\" : {\n",
+    "        \"api_key\" : deepseek_api_key,\n",
+    "        \"url\" : \"https://api.deepseek.com/v1\"\n",
+    "    },\n",
+    "    \"llama3.2\" : {\n",
+    "        \"api_key\" : \"ollama\",\n",
+    "        \"url\" : \"http://localhost:11434/v1\"\n",
+    "    },\n",
+    "    \"mistral\" : {\n",
+    "        \"api_key\" : \"ollama\",\n",
+    "        \"url\" : \"http://localhost:11434/v1\"\n",
+    "    }\n",
+    "}\n",
+    "\n",
+    "def create_model(model_name):\n",
+    "    spec = model_specs[model_name]\n",
+    "    if spec is None:\n",
+    "        return OpenAI()\n",
+    "    \n",
+    "    return OpenAI(api_key=spec[\"api_key\"], base_url=spec[\"url\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "orchestrator_model = \"gemini-2.0-flash\"\n",
+    "generator = create_model(orchestrator_model)\n",
+    "router = create_model(orchestrator_model)\n",
+    "\n",
+    "qa_models = {\n",
+    "    model_name : create_model(model_name) \n",
+    "    for model_name in model_specs.keys()\n",
+    "}\n",
+    "\n",
+    "judges = {\n",
+    "    model_name : create_model(model_name) \n",
+    "    for model_name, specs in model_specs.items() \n",
+    "    if not(specs) or specs[\"api_key\"] != \"ollama\"\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Orchestrator-Worker Workflow"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First, we generate a question to evaluate the intelligence of each LLM."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs \"\n",
+    "request += \"to evaluate and rank them based on their intelligence. \" \n",
+    "request += \"Answer **only** with the question, no explanation or preamble.\"\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]\n",
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = generator.chat.completions.create(\n",
+    "    model=orchestrator_model,\n",
+    "    messages=messages,\n",
+    ")\n",
+    "eval_question = response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display(Markdown(eval_question))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Task Parallelization"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, having the question and all the models instantiated it's time to see what each model has to say about the complex task it was given."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "question = [{\"role\": \"user\", \"content\": eval_question}]\n",
+    "answers = []\n",
+    "competitors = []\n",
+    "\n",
+    "for name, model in qa_models.items():\n",
+    "    response = model.chat.completions.create(model=name, messages=question)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    competitors.append(name)\n",
+    "    answers.append(answer)\n",
+    "\n",
+    "answers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "report = \"# Answer report for each of the 5 models\\n\\n\"\n",
+    "report += \"\\n\\n\".join([f\"## **Model: {model}**\\n\\n{answer}\" for model, answer in zip(competitors, answers)])\n",
+    "display(Markdown(report))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Synthetizer/Judge"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The Judge Agents ranks the LLM responses based on coherence and relevance to the evaluation prompt. Judges vote and the final LLM ranking is based on the aggregated ranking of all three judges."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\"\n",
+    "\n",
+    "together"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_prompt = f\"\"\"\n",
+    "                You are judging a competition between {len(competitors)} LLM competitors.\n",
+    "                Each model has been given this nuanced question to evaluate their intelligence:\n",
+    "\n",
+    "                {eval_question}\n",
+    "\n",
+    "                Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "                Respond with JSON, and only JSON, with the following format:\n",
+    "                {{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "                With 'best competitor number being ONLY the number', for instance:\n",
+    "                {{\"results\": [\"5\", \"2\", \"4\", ...]}}\n",
+    "                Here are the responses from each competitor:\n",
+    "\n",
+    "                {together}\n",
+    "\n",
+    "                Now respond with the JSON with the ranked order of the competitors, nothing else. Do NOT include MARKDOWN FORMATTING or CODE BLOCKS. ONLY the JSON\n",
+    "                \"\"\"\n",
+    "\n",
+    "judge_messages = [{\"role\": \"user\", \"content\": judge_prompt}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from collections import defaultdict\n",
+    "import re\n",
+    "\n",
+    "N = len(competitors)\n",
+    "scores = defaultdict(int)\n",
+    "for judge_name, judge in judges.items():\n",
+    "    response = judge.chat.completions.create(\n",
+    "        model=judge_name,\n",
+    "        messages=judge_messages,\n",
+    "    )\n",
+    "    response = response.choices[0].message.content\n",
+    "    response_json = re.findall(r'\\{.*?\\}', response)[0]\n",
+    "    results = json.loads(response_json)[\"results\"]\n",
+    "    ranks = [int(result) for result in results]\n",
+    "    print(f\"Judge {judge_name} ranking:\")\n",
+    "    for i, c in enumerate(ranks):\n",
+    "        model_name = competitors[c - 1]\n",
+    "        print(f\"#{i+1} : {model_name}\")\n",
+    "        scores[c - 1] += (N - i)\n",
+    "    print()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sorted_indices = sorted(scores, key=scores.get)\n",
+    "\n",
+    "# Convert to model names\n",
+    "ranked_model_names = [competitors[i] for i in sorted_indices]\n",
+    "\n",
+    "print(\"Final ranking from best to worst:\")\n",
+    "for i, name in enumerate(ranked_model_names[::-1], 1):\n",
+    "    print(f\"#{i}: {name}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Routing Workflow"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We now define a routing agent responsible for classifying task complexity and delegating the prompt to the most appropriate model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def classify_question_complexity(question: str, routing_agent, routing_model) -> int:\n",
+    "    \"\"\"\n",
+    "    Ask an LLM to classify the question complexity from 1 (easy) to 5 (very hard).\n",
+    "    \"\"\"\n",
+    "    prompt = f\"\"\"\n",
+    "        You are a classifier responsible for assigning a complexity level to user questions, based on how difficult they would be for a language model to answer.\n",
+    "\n",
+    "        Please read the question below and assign a complexity score from 1 to 5:\n",
+    "\n",
+    "        - Level 1: Very simple factual or definitional question (e.g., “What is the capital of France?”)\n",
+    "        - Level 2: Slightly more involved, requiring basic reasoning or comparison\n",
+    "        - Level 3: Moderate complexity, requiring synthesis, context understanding, or multi-part answers\n",
+    "        - Level 4: High complexity, requiring abstract thinking, ethical judgment, or creative generation\n",
+    "        - Level 5: Extremely challenging, requiring deep reasoning, philosophical reflection, or long-term multi-step inference\n",
+    "\n",
+    "        Respond ONLY with a single integer between 1 and 5 that best reflects the complexity of the question.\n",
+    "\n",
+    "        Question:\n",
+    "        {question}\n",
+    "        \"\"\"\n",
+    "\n",
+    "    response = routing_agent.chat.completions.create(\n",
+    "        model=routing_model,\n",
+    "        messages=[{\"role\": \"user\", \"content\": prompt}]\n",
+    "    )\n",
+    "    try:\n",
+    "        return int(response.choices[0].message.content.strip())\n",
+    "    except Exception:\n",
+    "        return 3  # default to medium complexity on error\n",
+    "    \n",
+    "def route_question_to_model(question: str, models_by_rank, classifier_model=router, model_name=orchestrator_model):\n",
+    "    level = classify_question_complexity(question, classifier_model, model_name)\n",
+    "    selected_model_name = models_by_rank[level - 1]\n",
+    "    return selected_model_name"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "difficulty_prompts = [\n",
+    "    \"Generate a very basic, factual question that a small or entry-level language model could answer easily. It should require no reasoning, just direct knowledge lookup.\",\n",
+    "    \"Generate a slightly involved question that requires basic reasoning, comparison, or combining two known facts. Still within the grasp of small models but not purely factual.\",\n",
+    "    \"Generate a moderately challenging question that requires some synthesis of ideas, multi-step reasoning, or contextual understanding. A mid-tier model should be able to answer it with effort.\",\n",
+    "    \"Generate a difficult question involving abstract thinking, open-ended reasoning, or ethical tradeoffs. The question should challenge large models to produce thoughtful and coherent responses.\",\n",
+    "    \"Generate an extremely complex and nuanced question that tests the limits of current language models. It should require deep reasoning, long-term planning, philosophy, or advanced multi-domain knowledge.\"\n",
+    "]\n",
+    "def generate_question(level, generator=generator, generator_model=orchestrator_model):\n",
+    "    prompt = (\n",
+    "        f\"{difficulty_prompts[level - 1]}\\n\"\n",
+    "        \"Answer only with the question, no explanation.\"\n",
+    "    )\n",
+    "    messages = [{\"role\": \"user\", \"content\": prompt}]\n",
+    "    response = generator.chat.completions.create(\n",
+    "        model=generator_model,  # or your planner model\n",
+    "        messages=messages\n",
+    "    )\n",
+    "    \n",
+    "    return response.choices[0].message.content\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Testing Routing Workflow"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Finally, to test the routing workflow, we create a function that accepts a task complexity level and triggers the full routing process.\n",
+    "\n",
+    "*Note: A level-N prompt isn't always assigned to the Nth-most capable model due to the classifier's subjective decisions.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_generation_routing(level):\n",
+    "    question = generate_question(level=level)\n",
+    "    answer_model = route_question_to_model(question, ranked_model_names)\n",
+    "    messages = [{\"role\": \"user\", \"content\": question}]\n",
+    "\n",
+    "    response =qa_models[answer_model].chat.completions.create(\n",
+    "            model=answer_model,  # or your planner model\n",
+    "            messages=messages\n",
+    "        )\n",
+    "    print(f\"Question : {question}\")\n",
+    "    print(f\"Routed to {answer_model}\")\n",
+    "    display(Markdown(response.choices[0].message.content))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generation_routing(level=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generation_routing(level=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generation_routing(level=3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generation_routing(level=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_generation_routing(level=5)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/1_medtech_opportunity_finder/01_medtech.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8c8f2d93",
+   "metadata": {},
+   "source": [
+    "# 🏥 MedTech AI Opportunity Finder\n",
+    "\n",
+    "- 🌍 Task: Generate quirky healthcare/pharma AI business opportunities with pain points and solutions.\n",
+    "- 🧠 Model: Uses OpenAI GPT-4o-mini for creative business idea generation\n",
+    "- 🎯 Process: Three-step pipeline - Business Area → Pain Point → AI Solution\n",
+    "- 📌 Output Format: Markdown-formatted responses streamed in real-time with humor\n",
+    "- 🔧 Tools: OpenAI API and IPython display for interactive streaming\n",
+    "- 🧑‍💻 Skill Level: Beginner\n",
+    "\n",
+    "🛠️ Requirements\n",
+    "- ⚙️ Hardware: ✅ CPU is sufficient — no GPU required\n",
+    "- 🔑 OpenAI API Key\n",
+    "- IPython environment (Jupyter/Colab)\n",
+    "\n",
+    "---\n",
+    "📢 Discover more Agentic AI notebooks on my [GitHub repository](https://github.com/lisekarimi/agentverse) and explore additional AI projects on my [portfolio](https://lisekarimi.com)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1df27837",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openai import OpenAI\n",
+    "from IPython.display import display, Markdown, update_display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b197c72a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client = OpenAI() # Automatically finds OPENAI_API_KEY without needing os.getenv() or load_dotenv()."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc8064bb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def stream_response(messages, section_title):\n",
+    "    \"\"\"Stream response and display with real-time updates\"\"\"\n",
+    "    response_stream = client.chat.completions.create(\n",
+    "        model=\"gpt-4o-mini\",\n",
+    "        messages=messages,\n",
+    "        stream=True\n",
+    "    )\n",
+    "\n",
+    "    response = \"\"\n",
+    "    display_handle = display(Markdown(f\"## {section_title}\\n\\n\"), display_id=True)\n",
+    "\n",
+    "    for chunk in response_stream:\n",
+    "        if chunk.choices[0].delta.content:\n",
+    "            response += chunk.choices[0].delta.content\n",
+    "            # Clean up any unwanted markdown artifacts\n",
+    "            cleaned_response = response.replace(\"```\", \"\").replace(\"markdown\", \"\")\n",
+    "            update_display(Markdown(f\"## {section_title}\\n\\n{cleaned_response}\"), display_id=display_handle.display_id)\n",
+    "\n",
+    "    return response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "857e0458",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 1: Business area\n",
+    "messages = [{\"role\": \"user\", \"content\": \"Give me a quirky healthcare or pharma business area for an AI agent. Keep it short and clear.\"}]\n",
+    "business_idea = stream_response(messages, \"🏢 Business Area\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23838465",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 2: Pain point\n",
+    "messages = [{\"role\": \"user\", \"content\": f\"What's broken about {business_idea}? Short and funny.\"}]\n",
+    "pain_point = stream_response(messages, \"😵 What's Broken\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5aa70151",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 3: AI solution\n",
+    "messages = [{\"role\": \"user\", \"content\": f\"How would an AI agent solve this {pain_point}? Brief and clear.\"}]\n",
+    "solution = stream_response(messages, \"🤖 AI to the Rescue\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agentverse",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

community_contributions/2_lab2-Evaluator-AnnpaS18.ipynb

@@ -0,0 +1,474 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2-judge-prompt-changed.ipynb

@@ -0,0 +1,476 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "Answer only the number for example\n",
+    "{{\"results\": [\"1\", \"2\", \"3\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2-parallelization.ipynb

@@ -0,0 +1,440 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Changes I've made with this lab.\n",
+    "1) Modified the original question to instead generate a range of questions, 12 of them.  These questions will be used to evaluate each LLM's reasoning, knowledge, creativity, and ability to handle nuanced scenarios.\n",
+    "2) I've changed this lab to run the queries in parallel.  Thanks GPT for helping with the code to do that.  :)\n",
+    "3) Instead of having one LLM rate all the responses, I have all of the LLM's rate each others work and then use a Borda Count to asign points to determine the winner."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "gemini_api_key = os.getenv('GEMINI_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if gemini_api_key:\n",
+    "    print(f\"Gemini API Key exists and begins {gemini_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Gemini API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"\"\"You are being evaluated for your reasoning, knowledge, creativity, and ability to handle nuanced scenarios. \n",
+    "Generate 12 questions that cover the following categories:\n",
+    "- Logical reasoning and problem solving\n",
+    "- Creative writing and storytelling\n",
+    "- Factual accuracy and knowledge recall\n",
+    "- Following instructions with strict constraints\n",
+    "- Multi-step planning and organization\n",
+    "- Ethical dilemmas and debatable issues\n",
+    "- Philosophical or abstract reasoning\n",
+    "- Summarization and explanation at different levels\n",
+    "- Translation and multilingual ability\n",
+    "- Roleplay or adaptive communication style\n",
+    "\n",
+    "Number each question from 1 to 12. \n",
+    "The result should be a balanced benchmark question set that fully tests an LLM’s capabilities.\n",
+    "\n",
+    "Important: Output only clean plain text. \n",
+    "Do not use any markup, formatting symbols, quotation marks, brackets, lists, or special characters \n",
+    "that could cause misinterpretation. Only provide plain text questions, one per line, numbered 1 to 20.\n",
+    "\"\"\"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate the questions.\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(question))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Ask the LLM's in Parallel\n",
+    "\n",
+    "import asyncio\n",
+    "\n",
+    "clients = {\n",
+    "    \"openai\": OpenAI(),\n",
+    "    \"claude\": Anthropic(),\n",
+    "    \"gemini\": OpenAI(api_key=gemini_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"),\n",
+    "    \"deepseek\": OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\"),\n",
+    "    \"groq\": OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\"),\n",
+    "}\n",
+    "\n",
+    "# Get the answers from the LLM\n",
+    "async def call_llm(model_name, messages):\n",
+    "    try:\n",
+    "        if \"claude\" in model_name:\n",
+    "            response = await asyncio.to_thread(\n",
+    "                clients[\"claude\"].messages.create,\n",
+    "                model=model_name,\n",
+    "                messages=messages,\n",
+    "                max_tokens=3000,\n",
+    "            )\n",
+    "            answer = \"\".join([c.text for c in response.content if c.type == \"text\"])\n",
+    "        \n",
+    "        elif \"gpt-4o-mini\" in model_name:\n",
+    "            response = await asyncio.to_thread(\n",
+    "                clients[\"openai\"].chat.completions.create,\n",
+    "                model=model_name,\n",
+    "                messages=messages,\n",
+    "            )\n",
+    "            answer = response.choices[0].message.content\n",
+    "\n",
+    "        elif \"gemini\" in model_name:\n",
+    "            response = await asyncio.to_thread(\n",
+    "                clients[\"gemini\"].chat.completions.create,\n",
+    "                model=model_name,\n",
+    "                messages=messages,\n",
+    "            )\n",
+    "            answer = response.choices[0].message.content\n",
+    "\n",
+    "        elif \"deepseek\" in model_name:\n",
+    "            response = await asyncio.to_thread(\n",
+    "                clients[\"deepseek\"].chat.completions.create,\n",
+    "                model=model_name,\n",
+    "                messages=messages,\n",
+    "            )\n",
+    "            answer = response.choices[0].message.content\n",
+    "\n",
+    "        elif \"llama\" in model_name:\n",
+    "            response = await asyncio.to_thread(\n",
+    "                clients[\"groq\"].chat.completions.create,\n",
+    "                model=model_name,\n",
+    "                messages=messages,\n",
+    "            )\n",
+    "            answer = response.choices[0].message.content\n",
+    "\n",
+    "        return model_name, answer        \n",
+    "\n",
+    "    except Exception as e:\n",
+    "        print (f\"❌ Error: {str(e)}\")\n",
+    "        return model_name, \"I was not able to generate answers for any of the questions.\"\n",
+    "\n",
+    "\n",
+    "# send out the calls to the LLM to ask teh questions.\n",
+    "async def ask_questions_in_parallel(messages):\n",
+    "    competitor_models = [\n",
+    "        \"gpt-4o-mini\",\n",
+    "        \"claude-3-7-sonnet-latest\",\n",
+    "        \"gemini-2.0-flash\",\n",
+    "        \"deepseek-chat\",\n",
+    "        \"llama-3.3-70b-versatile\"\n",
+    "    ]\n",
+    "\n",
+    "    # create tasks to call the LLM's in parallel\n",
+    "    tasks = [call_llm(model, messages) for model in competitor_models]\n",
+    "\n",
+    "    answers = []\n",
+    "    competitors = []\n",
+    "\n",
+    "    # When we have an answer, we can process it.  No waiting.\n",
+    "    for task in asyncio.as_completed(tasks):\n",
+    "        model_name, answer = await task\n",
+    "        competitors.append(model_name)\n",
+    "        answers.append(answer)\n",
+    "        print(f\"\\n✅ Got response from {model_name}\")\n",
+    "\n",
+    "    return competitors, answers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Fire off the ask to all the LLM's at once.  Parallelization...\n",
+    "competitors, answers = await ask_questions_in_parallel(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Look at the results\n",
+    "print (len(answers))\n",
+    "print (len(competitors))\n",
+    "print (competitors)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given the folowing questions:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your task is to evaluate the overall strength of the arguments presented by each competitor. \n",
+    "Consider the following factors:\n",
+    "- Clarity: how clearly the ideas are communicated\n",
+    "- Relevance: how directly the response addresses the question\n",
+    "- Depth: the level of reasoning, insight, or supporting evidence provided\n",
+    "- Persuasiveness: how compelling or convincing the response is overall\n",
+    "Respond with JSON, and only JSON.\n",
+    "The output must be a single JSON array of competitor names, ordered from best to worst.\n",
+    "Do not include any keys, labels, or extra text.\n",
+    "\n",
+    "Example format:\n",
+    "[\"1\", \"3\", \"5\", \"2\", \"4\"]\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\n",
+    "Do not deviate from the json format as described above.  Do not include the term ranking in the final json\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Have each LLM rate all of the results.\n",
+    "results = dict()\n",
+    "LLM_result = ''\n",
+    "\n",
+    "competitors, answers = await ask_questions_in_parallel(judge_messages)\n",
+    "\n",
+    "results = dict()\n",
+    "for index, each_competitor in enumerate(competitors):\n",
+    "    results[each_competitor] = answers[index].strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# See the results\n",
+    "print (len(answers))\n",
+    "results = dict()\n",
+    "for index, each_competitor in enumerate(competitors):\n",
+    "    results[each_competitor] = answers[index]\n",
+    "\n",
+    "print (results)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Lets convert these rankings into scores.  Borda Count - (1st gets 4, 2nd gets 3, etc.).\n",
+    "number_of_competitors = len(competitors)\n",
+    "scores = {}\n",
+    "\n",
+    "for rankings in results.values():\n",
+    "    print(rankings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Borda count points (1st gets n-1, 2nd gets n-2, etc.)\n",
+    "num_competitors = len(competitors)\n",
+    "\n",
+    "competitor_dict = dict()\n",
+    "for index, each_competitor in enumerate(competitors):\n",
+    "    competitor_dict[each_competitor] = index + 1\n",
+    "\n",
+    "borda_scores_dict = dict()\n",
+    "for each_competitor in competitors:\n",
+    "    if each_competitor not in borda_scores_dict:\n",
+    "        borda_scores_dict[each_competitor] = 0\n",
+    "\n",
+    "for voter_llm, ranking_str in results.items():\n",
+    "    ranking_indices = json.loads(ranking_str)\n",
+    "    ranking_indices = [int(x) for x in ranking_indices]\n",
+    "\n",
+    "    # For each position in the ranking, award points\n",
+    "    for position, competitor_index in enumerate(ranking_indices):\n",
+    "        competitor_name = competitors[competitor_index - 1]\n",
+    "\n",
+    "        # Borda count points (1st gets n-1, 2nd gets n-2, etc.)\n",
+    "        points = num_competitors - 1 - position  \n",
+    "        borda_scores_dict[competitor_name] += points\n",
+    "    \n",
+    "sorted_results = sorted(borda_scores_dict.items(), key=lambda x: x[1], reverse=True)\n",
+    "\n",
+    "print(f\"{'Rank':<4} {'LLM':<30} {'Points':<3}\")\n",
+    "print(\"-\" * 50)\n",
+    "\n",
+    "for rank, (llm, points) in enumerate(sorted_results, 1):\n",
+    "    print(f\"{rank:<4} {llm:<30} {points:<8}\")\n",
+    "\n",
+    "print(\"\\nQuestions asked:\")\n",
+    "print(question)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2.ipynb

@@ -0,0 +1,517 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os #allows the code to interact with the operating system\n",
+    "import json #imports Python's JSON library\n",
+    "from dotenv import load_dotenv #allows the code to load the .env file. A .env file must be explicity loaded\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True) #prioritizes the local .env file and will replace existing env variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI API Key exists and begins sk-proj-\n",
+      "Anthropic API Key not set (and this is optional)\n",
+      "Google API Key not set (and this is optional)\n",
+      "DeepSeek API Key not set (and this is optional)\n",
+      "Groq API Key not set (and this is optional)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation. I want the question to be related to the cruelty of life\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'role': 'user',\n",
+       "  'content': 'Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. Answer only with the question, no explanation.'}]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In a scenario where two intelligent agents with differing ethical frameworks encounter a moral dilemma involving a choice between the greater good and individual rights, how should they navigate their decision-making process, and what factors should they consider to justify their final actions?\n"
+     ]
+    }
+   ],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_Execution_measurement.py

@@ -0,0 +1,401 @@
+import os
+import json
+import asyncio
+import concurrent.futures
+import time
+from typing import Dict, List, Tuple, Optional
+from dotenv import load_dotenv
+from openai import OpenAI
+
+load_dotenv(override=True)
+
+openai = OpenAI()
+competitors = []
+answers = []
+together = ""
+openai_api_key = os.getenv('OPENAI_API_KEY')
+anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')
+google_api_key = os.getenv('GOOGLE_API_KEY')
+deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')
+groq_api_key = os.getenv('GROQ_API_KEY')
+
+models_dict = {
+    'openai': {
+        'model': 'gpt-4o-mini',
+        'api_key': openai_api_key,
+        'base_url': None
+    },
+    'gemini': {
+        'model': 'gemini-2.0-flash',
+        'api_key': google_api_key,
+        'base_url': 'https://generativelanguage.googleapis.com/v1beta/openai/'
+    },
+    'groq': {
+        'model': 'llama-3.3-70b-versatile',
+        'api_key': groq_api_key,
+        'base_url': 'https://api.groq.com/openai/v1'
+    },
+    'ollama': {
+        'model': 'llama3.2',
+        'api_key': 'ollama',
+        'base_url': 'http://localhost:11434/v1'
+    }
+}
+
+def key_checker():
+
+    if openai_api_key:
+        print(f"OpenAI API Key exists and begins {openai_api_key[:8]}")
+    else:
+        print("OpenAI API Key not set")
+        
+    if anthropic_api_key:
+        print(f"Anthropic API Key exists and begins {anthropic_api_key[:7]}")
+    else:
+        print("Anthropic API Key not set (and this is optional)")
+
+    if google_api_key:
+        print(f"Google API Key exists and begins {google_api_key[:2]}")
+    else:
+        print("Google API Key not set (and this is optional)")
+
+    if deepseek_api_key:
+        print(f"DeepSeek API Key exists and begins {deepseek_api_key[:3]}")
+    else:
+        print("DeepSeek API Key not set (and this is optional)")
+
+    if groq_api_key:
+        print(f"Groq API Key exists and begins {groq_api_key[:4]}")
+    else:
+        print("Groq API Key not set (and this is optional)")
+
+def question_prompt_generator():
+    request = "Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. "
+    request += "Answer only with the question, no explanation."
+    messages = [{"role": "user", "content": request}]
+    return messages
+
+def generate_competition_question():
+    """
+    Generate a challenging question for the LLM competition
+    Returns the question text and formatted messages for LLM calls
+    """
+    print("Generating competition question...")
+    question_prompt = question_prompt_generator()
+    question = llm_caller(question_prompt)
+    question_messages = [{"role": "user", "content": question}]
+    print(f"Question: \n{question}")
+    return question, question_messages
+
+def llm_caller(messages):
+    response = openai.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=messages,
+    )
+    return response.choices[0].message.content
+
+def llm_caller_with_model(messages, model_name, api_key, base_url):
+    llm = None
+
+    if base_url:
+        try:
+            llm = OpenAI(api_key=api_key, base_url=base_url)
+        except Exception as e:
+            print(f"Error creating OpenAI client: {e}")
+            return None
+    else:
+        try:
+            llm = OpenAI(api_key=api_key)
+        except Exception as e:
+            print(f"Error creating OpenAI client: {e}")
+            return None
+
+    response = llm.chat.completions.create(model=model_name, messages=messages)
+    return response.choices[0].message.content
+
+def get_single_model_answer(provider: str, details: Dict, question_messages: List[Dict]) -> Tuple[str, Optional[str]]:
+    """
+    Call a single model and return (provider, answer) or (provider, None) if failed.
+    This function is designed to be used with ThreadPoolExecutor.
+    """
+    print(f"Calling model {provider}...")
+    try:
+        answer = llm_caller_with_model(question_messages, details['model'], details['api_key'], details['base_url'])
+        print(f"Model {provider} was successfully called!")
+        return provider, answer
+    except Exception as e:
+        print(f"Model {provider} failed to call: {e}")
+        return provider, None
+
+def get_models_answers(question_messages):
+    """
+    Sequential version - kept for backward compatibility
+    """
+    for provider, details in models_dict.items():
+        print(f"Calling model {provider}...")
+        try:
+            answer = llm_caller_with_model(question_messages, details['model'], details['api_key'], details['base_url'])
+            print(f"Model {provider} was successful called!")
+        except Exception as e:
+            print(f"Model {provider} failed to call: {e}")
+            continue
+        competitors.append(provider)
+        answers.append(answer)
+
+def get_models_answers_parallel(question_messages, max_workers: int = 4):
+    """
+    Parallel version - calls all models simultaneously using ThreadPoolExecutor
+    """
+    print("Starting parallel execution of all models...")
+    
+    # Clear previous results
+    competitors.clear()
+    answers.clear()
+    
+    # Use ThreadPoolExecutor for parallel execution
+    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
+        # Submit all tasks
+        future_to_provider = {
+            executor.submit(get_single_model_answer, provider, details, question_messages): provider 
+            for provider, details in models_dict.items()
+        }
+        
+        # Collect results as they complete
+        for future in concurrent.futures.as_completed(future_to_provider):
+            provider, answer = future.result()
+            if answer is not None:  # Only add successful calls
+                competitors.append(provider)
+                answers.append(answer)
+    
+    print(f"Parallel execution completed. {len(competitors)} models responded successfully.")
+
+async def get_single_model_answer_async(provider: str, details: Dict, question_messages: List[Dict]) -> Tuple[str, Optional[str]]:
+    """
+    Async version of single model call - for even better performance
+    """
+    print(f"Calling model {provider} (async)...")
+    try:
+        # Run the synchronous call in a thread pool
+        loop = asyncio.get_event_loop()
+        answer = await loop.run_in_executor(
+            None, 
+            llm_caller_with_model, 
+            question_messages, 
+            details['model'], 
+            details['api_key'], 
+            details['base_url']
+        )
+        print(f"Model {provider} was successfully called!")
+        return provider, answer
+    except Exception as e:
+        print(f"Model {provider} failed to call: {e}")
+        return provider, None
+
+async def get_models_answers_async(question_messages):
+    """
+    Async version - calls all models simultaneously using asyncio
+    """
+    print("Starting async execution of all models...")
+    
+    # Clear previous results
+    competitors.clear()
+    answers.clear()
+    
+    # Create tasks for all models
+    tasks = [
+        get_single_model_answer_async(provider, details, question_messages)
+        for provider, details in models_dict.items()
+    ]
+    
+    # Wait for all tasks to complete
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+    
+    # Process results
+    for result in results:
+        if isinstance(result, Exception):
+            print(f"Task failed with exception: {result}")
+            continue
+        provider, answer = result
+        if answer is not None:  # Only add successful calls
+            competitors.append(provider)
+            answers.append(answer)
+    
+    print(f"Async execution completed. {len(competitors)} models responded successfully.")
+
+def together_maker(answers):
+    together = ""
+    for index, answer in enumerate(answers):
+        together += f"# Response from competitor {index+1}\n\n"
+        together += answer + "\n\n"    
+    return together
+
+def judge_prompt_generator(competitors, question, together):
+    judge = f"""You are judging a competition between {len(competitors)} competitors.
+    Each model has been given this question:
+
+    {question}
+
+    Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.
+    Respond with JSON, and only JSON, with the following format:
+    {{"results": ["best competitor number", "second best competitor number", "third best competitor number", ...]}}
+
+    Here are the responses from each competitor:
+
+    {together}
+
+    Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks."""
+    return judge
+
+def judge_caller(judge_prompt, competitors):
+    print(f"Calling judge...")
+    judge_messages = [{"role": "user", "content": judge_prompt}]
+    results = llm_caller_with_model(judge_messages, "o3-mini", openai_api_key, None)
+    results_dict = json.loads(results)
+    ranks = results_dict["results"]
+    for index, result in enumerate(ranks):
+        competitor = competitors[int(result)-1]
+        print(f"Rank {index+1}: {competitor}")
+    return ranks
+
+def compare_execution_methods(question_messages, runs_per_method=1):
+    """
+    Compare performance of different execution methods
+    """
+    methods = ['sequential', 'parallel', 'async']
+    results = {}
+    
+    for method in methods:
+        print(f"\n{'='*50}")
+        print(f"Testing {method} execution method")
+        print(f"{'='*50}")
+        
+        method_times = []
+        
+        for run in range(runs_per_method):
+            print(f"\nRun {run + 1}/{runs_per_method}")
+            
+            # Clear previous results
+            competitors.clear()
+            answers.clear()
+            
+            start_time = time.time()
+            
+            if method == 'sequential':
+                get_models_answers(question_messages)
+            elif method == 'parallel':
+                get_models_answers_parallel(question_messages, max_workers=4)
+            elif method == 'async':
+                asyncio.run(get_models_answers_async(question_messages))
+            
+            execution_time = time.time() - start_time
+            method_times.append(execution_time)
+            print(f"Run {run + 1} completed in {execution_time:.2f} seconds")
+        
+        avg_time = sum(method_times) / len(method_times)
+        results[method] = {
+            'times': method_times,
+            'avg_time': avg_time,
+            'successful_models': len(competitors)
+        }
+        
+        print(f"\n{method.upper()} Results:")
+        print(f"  Average time: {avg_time:.2f} seconds")
+        print(f"  Successful models: {len(competitors)}")
+        print(f"  All times: {[f'{t:.2f}s' for t in method_times]}")
+    
+    # Print comparison summary
+    print(f"\n{'='*60}")
+    print("PERFORMANCE COMPARISON SUMMARY")
+    print(f"{'='*60}")
+    
+    for method, data in results.items():
+        print(f"{method.upper():>12}: {data['avg_time']:>6.2f}s avg, {data['successful_models']} models")
+    
+    # Calculate speedup
+    if 'sequential' in results:
+        seq_time = results['sequential']['avg_time']
+        print(f"\nSpeedup vs Sequential:")
+        for method, data in results.items():
+            if method != 'sequential':
+                speedup = seq_time / data['avg_time']
+                print(f"  {method.upper()}: {speedup:.2f}x faster")
+    
+    return results
+
+def run_llm_competition(question_messages, execution_method, question):
+    """
+    Run the LLM competition with the specified execution method
+    """
+    print(f"\nUsing {execution_method} execution method...")
+    start_time = time.time()
+
+    if execution_method == 'sequential':
+        get_models_answers(question_messages)
+    elif execution_method == 'parallel':
+        get_models_answers_parallel(question_messages, max_workers=4)
+    elif execution_method == 'async':
+        asyncio.run(get_models_answers_async(question_messages))
+    else:
+        raise ValueError(f"Unknown execution method: {execution_method}")
+
+    execution_time = time.time() - start_time
+    print(f"Execution completed in {execution_time:.2f} seconds")
+
+    together = together_maker(answers)
+    judge_prompt = judge_prompt_generator(competitors, question, together)
+    judge_caller(judge_prompt, competitors)
+    
+    return execution_time
+
+# Interactive execution method selection
+def get_execution_method():
+    """
+    Prompt user to select execution method
+    """
+    print("\n" + "="*60)
+    print("EXECUTION METHOD SELECTION")
+    print("="*60)
+    print("Choose how to execute the LLM calls:")
+    print("1. Sequential - Call models one after another (original method)")
+    print("2. Parallel   - Call all models simultaneously (recommended)")
+    print("3. Async      - Use async/await for maximum performance")
+    print("4. Compare    - Run all methods and compare performance")
+    print("="*60)
+    
+    while True:
+        try:
+            choice = input("Enter your choice (1-4): ").strip()
+            
+            if choice == '1':
+                return 'sequential'
+            elif choice == '2':
+                return 'parallel'
+            elif choice == '3':
+                return 'async'
+            elif choice == '4':
+                return 'compare'
+            else:
+                print("Invalid choice. Please enter 1, 2, 3, or 4.")
+                continue
+        except KeyboardInterrupt:
+            print("\nExiting...")
+            exit(0)
+        except EOFError:
+            print("\nExiting...")
+            exit(0)
+
+def main():
+    key_checker()
+    
+    # Get user's execution method choice
+    EXECUTION_METHOD = get_execution_method()
+    # Generate the competition question and get the question messages
+    question, question_messages = generate_competition_question()
+
+    if EXECUTION_METHOD == 'compare':
+        print("\nRunning performance comparison...")
+        compare_execution_methods(question_messages, runs_per_method=1)
+    else:
+     run_llm_competition(question_messages, EXECUTION_METHOD, question)
+
+main()

community_contributions/2_lab2_ReAct_Pattern.ipynb

@@ -0,0 +1,289 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ReAct Pattern"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openai\n",
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "import io\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "from openai import OpenAI\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "\n",
+    "# Request prompt\n",
+    "request = (\n",
+    "    \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "    \"Answer only with the question, no explanation.\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "\n",
+    "def generate_question(prompt: str) -> str:\n",
+    "    response = openai.chat.completions.create(\n",
+    "        model='gpt-4o-mini',\n",
+    "        messages=[{'role': 'user', 'content': prompt}]\n",
+    "    )\n",
+    "    question = response.choices[0].message.content\n",
+    "    return question\n",
+    "\n",
+    "def react_agent_decide_model(question: str) -> str:\n",
+    "    prompt = f\"\"\"\n",
+    "            You are an intelligent AI assistant tasked with evaluating which language model is most suitable to answer a given question.\n",
+    "\n",
+    "            Available models:\n",
+    "            - OpenAI: excels at reasoning and factual answers.\n",
+    "            - Claude: better for philosophical, nuanced, and ethical topics.\n",
+    "            - Gemini: good for concise and structured summaries.\n",
+    "            - Groq: good for creative or exploratory tasks.\n",
+    "            - DeepSeek: strong at coding, technical reasoning, and multilingual responses.\n",
+    "\n",
+    "            Here is the question to answer:\n",
+    "            \"{question}\"\n",
+    "\n",
+    "            ### Thought:\n",
+    "            Which model is best suited to answer this question, and why?\n",
+    "\n",
+    "            ### Action:\n",
+    "            Respond with only the model name you choose (e.g., \"Claude\").\n",
+    "                \"\"\"\n",
+    "\n",
+    "    response = openai.chat.completions.create(\n",
+    "        model=\"o3-mini\",\n",
+    "        messages=[{\"role\": \"user\", \"content\": prompt}]\n",
+    "    )\n",
+    "    model = response.choices[0].message.content.strip()\n",
+    "    return model\n",
+    "\n",
+    "def generate_answer_openai(prompt):\n",
+    "    answer = openai.chat.completions.create(\n",
+    "            model='gpt-4o-mini',\n",
+    "            messages=[{'role': 'user', 'content': prompt}]\n",
+    "        ).choices[0].message.content\n",
+    "    return answer\n",
+    "\n",
+    "def generate_answer_anthropic(prompt):\n",
+    "    anthropic = Anthropic(api_key=anthropic_api_key)\n",
+    "    model_name = \"claude-3-5-sonnet-20240620\"\n",
+    "    answer = anthropic.messages.create(\n",
+    "            model=model_name,\n",
+    "            messages=[{'role': 'user', 'content': prompt}],\n",
+    "            max_tokens=1000\n",
+    "        ).content[0].text\n",
+    "    return answer\n",
+    "\n",
+    "def generate_answer_deepseek(prompt):\n",
+    "    deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "    model_name = \"deepseek-chat\"    \n",
+    "    answer = deepseek.chat.completions.create(\n",
+    "            model=model_name,\n",
+    "            messages=[{'role': 'user', 'content': prompt}],\n",
+    "            base_url='https://api.deepseek.com/v1'\n",
+    "        ).choices[0].message.content\n",
+    "    return answer\n",
+    "\n",
+    "def generate_answer_gemini(prompt):\n",
+    "    gemini=OpenAI(base_url='https://generativelanguage.googleapis.com/v1beta/openai/',api_key=google_api_key)\n",
+    "    model_name = \"gemini-2.0-flash\"\n",
+    "    answer = gemini.chat.completions.create(\n",
+    "            model=model_name,\n",
+    "            messages=[{'role': 'user', 'content': prompt}],\n",
+    "        ).choices[0].message.content\n",
+    "    return answer\n",
+    "\n",
+    "def generate_answer_groq(prompt):\n",
+    "    groq=OpenAI(base_url='https://api.groq.com/openai/v1',api_key=groq_api_key)\n",
+    "    model_name=\"llama3-70b-8192\"\n",
+    "    answer = groq.chat.completions.create(\n",
+    "            model=model_name,\n",
+    "            messages=[{'role': 'user', 'content': prompt}],\n",
+    "            base_url=\"https://api.groq.com/openai/v1\"\n",
+    "        ).choices[0].message.content\n",
+    "    return answer\n",
+    "\n",
+    "def main():\n",
+    "    print(\"Generating question...\")\n",
+    "    question = generate_question(request)\n",
+    "    print(f\"\\n🧠 Question: {question}\\n\")\n",
+    "    selected_model = react_agent_decide_model(question)\n",
+    "    print(f\"\\n🔹 {selected_model}:\\n\")\n",
+    "    \n",
+    "    if selected_model.lower() == \"openai\":\n",
+    "        answer = generate_answer_openai(question)\n",
+    "    elif selected_model.lower() == \"deepseek\":\n",
+    "        answer = generate_answer_deepseek(question)\n",
+    "    elif selected_model.lower() == \"gemini\":\n",
+    "        answer = generate_answer_gemini(question)\n",
+    "    elif selected_model.lower() == \"groq\":\n",
+    "        answer = generate_answer_groq(question)\n",
+    "    elif selected_model.lower() == \"claude\":\n",
+    "        answer = generate_answer_anthropic(question)\n",
+    "    print(f\"\\n🔹 {selected_model}:\\n{answer}\\n\")\n",
+    "    \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "main()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_akash_parallelization.ipynb

@@ -0,0 +1,295 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI, AsyncOpenAI\n",
+    "from IPython.display import Markdown, display\n",
+    "import asyncio\n",
+    "from functools import partial"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = AsyncOpenAI()\n",
+    "response = await openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dataclasses import dataclass\n",
+    "\n",
+    "@dataclass\n",
+    "class LLMResource:\n",
+    "    api_key: str\n",
+    "    model: str\n",
+    "    url: str = None # optional otherwise NOone\n",
+    "\n",
+    "llm_resources = [\n",
+    "    LLMResource(api_key=openai_api_key, model=\"gpt-4o-mini\"),\n",
+    "    LLMResource(api_key=google_api_key, model=\"gemini-2.5-flash\", url=\"https://generativelanguage.googleapis.com/v1beta/openai/\"),\n",
+    "    LLMResource(api_key=groq_api_key, model=\"qwen/qwen3-32b\", url=\"https://api.groq.com/openai/v1\"),\n",
+    "    LLMResource(api_key=\"ollama\", model=\"deepseek-r1:1.5b\", url=\"http://localhost:11434/v1\" )\n",
+    "]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "async def llm_call(key, model_name, url, messages) -> tuple:\n",
+    "    if url is None:\n",
+    "        llm = AsyncOpenAI(api_key=key)\n",
+    "    else: \n",
+    "        llm = AsyncOpenAI(base_url=url,api_key=key)\n",
+    "    \n",
+    "    response = await llm.chat.completions.create(\n",
+    "        model=model_name, messages=messages)\n",
+    "    \n",
+    "    answer = (model_name, response.choices[0].message.content)\n",
+    "\n",
+    "    return answer #returns tuple of modle and response from LLM\n",
+    "\n",
+    "llm_callable = partial(llm_call, messages=messages) #prefill with messages\n",
+    "# Always remember to do this!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#gather all responses concurrently\n",
+    "tasks = [llm_callable(res.api_key,res.model,res.url) for res in llm_resources]\n",
+    "results =  await asyncio.gather(*tasks)\n",
+    "together =  [f'Response from competitor {model}:{answer}' for model,answer in results]#gather results once all model finish running\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(llm_resources)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{request}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together} # all responses\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors name, nothing else. Do not include markdown formatting or code blocks.\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "\n",
+    "ranks = results_dict[\"results\"]\n",
+    "\n",
+    "for index, result in enumerate(ranks):\n",
+    "    print(f\"Rank {index+1}: {result}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_async.ipynb

@@ -0,0 +1,474 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "import asyncio\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI, AsyncOpenAI\n",
+    "from anthropic import AsyncAnthropic\n",
+    "from pydantic import BaseModel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')\n",
+    "ANTHROPIC_API_KEY = os.getenv('ANTHROPIC_API_KEY')\n",
+    "GOOGLE_API_KEY = os.getenv('GOOGLE_API_KEY')\n",
+    "DEEPSEEK_API_KEY = os.getenv('DEEPSEEK_API_KEY')\n",
+    "GROQ_API_KEY = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if OPENAI_API_KEY:\n",
+    "    print(f\"OpenAI API Key exists and begins {OPENAI_API_KEY[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if ANTHROPIC_API_KEY:\n",
+    "    print(f\"Anthropic API Key exists and begins {ANTHROPIC_API_KEY[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if GOOGLE_API_KEY:\n",
+    "    print(f\"Google API Key exists and begins {GOOGLE_API_KEY[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if DEEPSEEK_API_KEY:\n",
+    "    print(f\"DeepSeek API Key exists and begins {DEEPSEEK_API_KEY[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if GROQ_API_KEY:\n",
+    "    print(f\"Groq API Key exists and begins {GROQ_API_KEY[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = AsyncOpenAI()\n",
+    "response = await openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define Pydantic model for storing LLM results\n",
+    "class LLMResult(BaseModel):\n",
+    "    model: str\n",
+    "    answer: str\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results: list[LLMResult] = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "async def openai_answer() -> None:\n",
+    "\n",
+    "  if OPENAI_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"OpenAI starting!\")\n",
+    "  model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "  try:\n",
+    "    response = await openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with OpenAI: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"OpenAI done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "async def anthropic_answer() -> None:\n",
+    "\n",
+    "  if ANTHROPIC_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Anthropic starting!\")\n",
+    "  model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "  claude = AsyncAnthropic()\n",
+    "  try:\n",
+    "    response = await claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "    answer = response.content[0].text\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Anthropic: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Anthropic done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def google_answer() -> None:\n",
+    "\n",
+    "  if GOOGLE_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Google starting!\")\n",
+    "  model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "  gemini = AsyncOpenAI(api_key=GOOGLE_API_KEY, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "  try:\n",
+    "    response = await gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer =  response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Google: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Google done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def deepseek_answer() -> None:\n",
+    "\n",
+    "  if DEEPSEEK_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"DeepSeek starting!\")\n",
+    "  model_name = \"deepseek-chat\"\n",
+    "\n",
+    "  deepseek = AsyncOpenAI(api_key=DEEPSEEK_API_KEY, base_url=\"https://api.deepseek.com/v1\")\n",
+    "  try:\n",
+    "    response = await deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with DeepSeek: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"DeepSeek done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def groq_answer() -> None:\n",
+    "\n",
+    "  if GROQ_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Groq starting!\")\n",
+    "  model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "  groq = AsyncOpenAI(api_key=GROQ_API_KEY, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "  try:\n",
+    "    response = await groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Groq: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Groq done!\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def ollama_answer() -> None:\n",
+    "  model_name = \"llama3.2\"\n",
+    "\n",
+    "  print(\"Ollama starting!\")\n",
+    "  ollama = AsyncOpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "  try:\n",
+    "    response = await ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Ollama: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Ollama done!\") "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def gather_answers():\n",
+    "  tasks = [\n",
+    "    openai_answer(),\n",
+    "    anthropic_answer(),\n",
+    "    google_answer(),\n",
+    "    deepseek_answer(),\n",
+    "    groq_answer(),\n",
+    "    ollama_answer()\n",
+    "  ]\n",
+    "  await asyncio.gather(*tasks)\n",
+    "\n",
+    "await gather_answers()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "together = \"\"\n",
+    "competitors = []\n",
+    "answers = []\n",
+    "\n",
+    "for res in results:\n",
+    "    competitor = res.model\n",
+    "    answer = res.answer\n",
+    "    competitors.append(competitor)\n",
+    "    answers.append(answer)\n",
+    "    together += f\"# Response from competitor {competitor}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\"\n",
+    "\n",
+    "print(f\"Number of competitors: {len(results)}\")\n",
+    "print(together)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(results)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "judgement = response.choices[0].message.content\n",
+    "print(judgement)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(judgement)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, comp in enumerate(ranks):\n",
+    "    print(f\"Rank {index+1}: {comp}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_async_with_reasons.ipynb

@@ -0,0 +1,490 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This was derived from 2_lab2_async. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "import asyncio\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI, AsyncOpenAI\n",
+    "from anthropic import AsyncAnthropic\n",
+    "from pydantic import BaseModel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')\n",
+    "ANTHROPIC_API_KEY = os.getenv('ANTHROPIC_API_KEY')\n",
+    "GOOGLE_API_KEY = os.getenv('GOOGLE_API_KEY')\n",
+    "DEEPSEEK_API_KEY = os.getenv('DEEPSEEK_API_KEY')\n",
+    "GROQ_API_KEY = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if OPENAI_API_KEY:\n",
+    "    print(f\"OpenAI API Key exists and begins {OPENAI_API_KEY[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if ANTHROPIC_API_KEY:\n",
+    "    print(f\"Anthropic API Key exists and begins {ANTHROPIC_API_KEY[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if GOOGLE_API_KEY:\n",
+    "    print(f\"Google API Key exists and begins {GOOGLE_API_KEY[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if DEEPSEEK_API_KEY:\n",
+    "    print(f\"DeepSeek API Key exists and begins {DEEPSEEK_API_KEY[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if GROQ_API_KEY:\n",
+    "    print(f\"Groq API Key exists and begins {GROQ_API_KEY[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = AsyncOpenAI()\n",
+    "response = await openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define Pydantic model for storing LLM results\n",
+    "class LLMResult(BaseModel):\n",
+    "    model: str\n",
+    "    answer: str\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results: list[LLMResult] = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "async def openai_answer() -> None:\n",
+    "\n",
+    "  if OPENAI_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"OpenAI starting!\")\n",
+    "  model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "  try:\n",
+    "    response = await openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with OpenAI: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"OpenAI done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "async def anthropic_answer() -> None:\n",
+    "\n",
+    "  if ANTHROPIC_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Anthropic starting!\")\n",
+    "  model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "  claude = AsyncAnthropic()\n",
+    "  try:\n",
+    "    response = await claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "    answer = response.content[0].text\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Anthropic: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Anthropic done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def google_answer() -> None:\n",
+    "\n",
+    "  if GOOGLE_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Google starting!\")\n",
+    "  model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "  gemini = AsyncOpenAI(api_key=GOOGLE_API_KEY, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "  try:\n",
+    "    response = await gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer =  response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Google: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Google done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def deepseek_answer() -> None:\n",
+    "\n",
+    "  if DEEPSEEK_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"DeepSeek starting!\")\n",
+    "  model_name = \"deepseek-chat\"\n",
+    "\n",
+    "  deepseek = AsyncOpenAI(api_key=DEEPSEEK_API_KEY, base_url=\"https://api.deepseek.com/v1\")\n",
+    "  try:\n",
+    "    response = await deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with DeepSeek: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"DeepSeek done!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def groq_answer() -> None:\n",
+    "\n",
+    "  if GROQ_API_KEY is None:\n",
+    "    return None\n",
+    "  \n",
+    "  print(\"Groq starting!\")\n",
+    "  model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "  groq = AsyncOpenAI(api_key=GROQ_API_KEY, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "  try:\n",
+    "    response = await groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Groq: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Groq done!\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def ollama_answer() -> None:\n",
+    "  model_name = \"llama3.2\"\n",
+    "\n",
+    "  print(\"Ollama starting!\")\n",
+    "  ollama = AsyncOpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "  try:\n",
+    "    response = await ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    results.append(LLMResult(model=model_name, answer=answer))\n",
+    "  except Exception as e:\n",
+    "    print(f\"Error with Ollama: {e}\")\n",
+    "    return None\n",
+    "\n",
+    "  print(\"Ollama done!\") "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def gather_answers():\n",
+    "  tasks = [\n",
+    "    openai_answer(),\n",
+    "    anthropic_answer(),\n",
+    "    google_answer(),\n",
+    "    deepseek_answer(),\n",
+    "    groq_answer(),\n",
+    "    ollama_answer()\n",
+    "  ]\n",
+    "  await asyncio.gather(*tasks)\n",
+    "\n",
+    "await gather_answers()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "together = \"\"\n",
+    "competitors = []\n",
+    "answers = []\n",
+    "\n",
+    "for res in results:\n",
+    "    competitor = res.model\n",
+    "    answer = res.answer\n",
+    "    competitors.append(competitor)\n",
+    "    answers.append(answer)\n",
+    "    together += f\"# Response from competitor {competitor}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\"\n",
+    "\n",
+    "print(f\"Number of competitors: {len(results)}\")\n",
+    "print(together)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(results)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...],\n",
+    "\"explanations\": [\"explanation for each rank\", \"explanation for each rank\", \"explanation for each rank\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "judgement = response.choices[0].message.content\n",
+    "print(judgement)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(judgement)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "explanations = results_dict[\"explanations\"]\n",
+    "for index, comp in enumerate(ranks):\n",
+    "    print(f\"Rank {index+1}: {comp} \\n\\t{explanations[index]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_doclee99_gpt5_improves_gemini.25flash.ipynb

@@ -0,0 +1,620 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# print(together)\n",
+    "display(Markdown(together))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Implement Evaluator-Optimizer workflow design pattern - An Optimizer LLM analyzes the response of the top-ranked competitor\n",
+    "# and creates a system prompt designed to improve the response. The system prompot is then\n",
+    "# sent back to the top-ranked competitor to deliver a new response.  \n",
+    "# The optimizer LLM then compares the new response to the old response and surmises\n",
+    "# what aspects of the system prompt may be responsible for the differences in the responses.\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Get the top competitor (model name) and their response\n",
+    "top_rank_index = int(ranks[0]) - 1\n",
+    "top_competitor_name = competitors[top_rank_index]\n",
+    "top_competitor_response = answers[top_rank_index]\n",
+    "top_competitor_prompt = question\n",
+    "\n",
+    "# Compose a system prompt for GPT-5 to act as an expert evaluator of question quality and answer depth\n",
+    "system_prompt = (\n",
+    "    \"You are an expert evaluator of LLM prompt quality and answer depth. \"\n",
+    "    \"Your task is to analyze the comprehensiveness and depth of thought in the following answer, \"\n",
+    "    \"which was generated by a language model in response to a challenging question. \"\n",
+    "    \"Consider aspects such as completeness, insight, reasoning, and nuance. \"\n",
+    "    \"Provide a detailed analysis of the answer's strengths and weaknesses and store in the 'markdown_analysis' property.\"\n",
+    "    \"Generate a suggested system prompt that will improve the answer and store in the 'system_prompt' property.\"\n",
+    ")\n",
+    "\n",
+    "# Compose the user prompt for GPT-5\n",
+    "user_prompt = (\n",
+    "    f\"Prompt:\\n{top_competitor_prompt}\\n\\n\"\n",
+    "    f\"Answer:\\n{top_competitor_response}\\n\\n\"\n",
+    "    \"Please analyze the comprehensiveness and depth of thought of the above answer. \"\n",
+    "    \"Discuss its strengths and weaknesses in detail.\"\n",
+    ")\n",
+    "\n",
+    "# Call GPT-5 to perform the evaluation\n",
+    "gpt5 = OpenAI()\n",
+    "\n",
+    "# Define the tool schema\n",
+    "tools = [\n",
+    "    {\n",
+    "        \"type\": \"function\",\n",
+    "        \"function\": {\n",
+    "            \"name\": \"markdown_and_structured_data\",\n",
+    "            \"description\": \"Provide both markdown analysis and structured data\",\n",
+    "            \"parameters\": {\n",
+    "                \"type\": \"object\",\n",
+    "                \"properties\": {\n",
+    "                    \"markdown_analysis\": {\n",
+    "                        \"type\": \"string\",\n",
+    "                        \"description\": \"Detailed markdown analysis\"\n",
+    "                    },\n",
+    "                    \"system_prompt\": {\n",
+    "                        \"type\": \"string\"\n",
+    "                    }\n",
+    "                },\n",
+    "                \"required\": [\"markdown_analysis\", \"sentiment\", \"confidence\", \"key_phrases\"]\n",
+    "            }\n",
+    "        }\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "gpt5_response = gpt5.chat.completions.create(\n",
+    "    model=\"gpt-5\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"system\", \"content\": system_prompt},\n",
+    "        {\"role\": \"user\", \"content\": user_prompt}\n",
+    "    ],\n",
+    "    tools=tools,\n",
+    "    tool_choice={\"type\": \"function\", \"function\": {\"name\": \"markdown_and_structured_data\"}}\n",
+    ")\n",
+    "\n",
+    "tool_call = gpt5_response.choices[0].message.tool_calls[0]\n",
+    "arguments = json.loads(tool_call.function.arguments)\n",
+    "\n",
+    "markdown_analysis = arguments[\"markdown_analysis\"]\n",
+    "system_prompt = arguments[\"system_prompt\"]\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Display the evaluation\n",
+    "from IPython.display import Markdown, display\n",
+    "display(Markdown(\"### GPT-5 Evaluation of Top Competitor's Answer\"))\n",
+    "display(Markdown(f\"Top Competitor: {top_competitor_name}\"))\n",
+    "display(Markdown(markdown_analysis))\n",
+    "display(Markdown(\"### Suggested System Prompt\"))\n",
+    "display(Markdown(system_prompt))\n",
+    "\n",
+    "\n",
+    "# The top competitor was gemini-2.0-flash, so send the original question and suggested system prompt to generate a new response\n",
+    "# Send the system_prompt and original question to gemini-2.0-flash to generate a new answer\n",
+    "\n",
+    "gemini_response = gemini.chat.completions.create(\n",
+    "    model=\"gemini-2.0-flash\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"system\", \"content\": system_prompt},\n",
+    "        {\"role\": \"user\", \"content\": question}\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "new_answer = gemini_response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(\"### Gemini-2.0-Flash New Answer with Suggested System Prompt\"))\n",
+    "display(Markdown(new_answer))\n",
+    "\n",
+    "comparison_prompt = f\"\"\"You are an expert LLM evaluator. Compare the following two answers to the same question, where the only difference is that the second answer was generated using a system prompt suggested by you (GPT-5) after evaluating the first answer.\n",
+    "\n",
+    "Original Answer (from {top_competitor_name}):\n",
+    "{top_competitor_response}\n",
+    "\n",
+    "New Answer (from {top_competitor_name} with your system prompt):\n",
+    "{new_answer}\n",
+    "\n",
+    "System Prompt Used for New Answer:\n",
+    "{system_prompt}\n",
+    "\n",
+    "Please analyze:\n",
+    "- What are the key differences between the two answers?\n",
+    "- What aspects of the system prompt likely contributed to these differences?\n",
+    "- Did the system prompt improve the quality, accuracy, or style of the answer? How?\n",
+    "- Any remaining limitations or further suggestions.\n",
+    "\n",
+    "Provide a detailed, structured analysis.\n",
+    "\"\"\"\n",
+    "\n",
+    "gpt5_comparison_response = gpt5.chat.completions.create(\n",
+    "    model=\"gpt-5\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"system\", \"content\": \"You are an expert LLM evaluator.\"},\n",
+    "        {\"role\": \"user\", \"content\": comparison_prompt}\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "comparison_analysis = gpt5_comparison_response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(\"### GPT-5 Analysis: Impact of System Prompt on Gemini-2.0-Flash's Answer\"))\n",
+    "display(Markdown(comparison_analysis))\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_evaluator_mars.ipynb

@@ -0,0 +1,677 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Note - update since the videos\n",
+    "\n",
+    "I've updated the model names to use the latest models below, like GPT 5 and Claude Sonnet 4.5. It's worth noting that these models can be quite slow - like 1-2 minutes - but they do a great job! Feel free to switch them for faster models if you'd prefer, like the ones I use in the video."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "# I've updated this with the latest model, but it can take some time because it likes to think!\n",
+    "# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins\n",
+    "\n",
+    "model_name = \"gpt-5-nano\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-sonnet-4-5\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=5000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.5-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Updated with the latest Open Source model from OpenAI\n",
+    "\n",
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"openai/gpt-oss-120b\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time! from Claude\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=\"claude-sonnet-4-5\", messages=judge_messages, max_tokens=5000)\n",
+    "results_claude = response.content[0].text\n",
+    "\n",
+    "print(results_claude)\n",
+    "\n",
+    "results_claude_tab = json.loads(results_claude)\n",
+    "ranks = results_claude_tab[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time! from Gemini\n",
+    "\n",
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "response = gemini.chat.completions.create(\n",
+    "    model=\"gemini-2.5-flash\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results_gemini = response.choices[0].message.content\n",
+    "print(results_gemini)\n",
+    "\n",
+    "results_gemini_tab = json.loads(results_gemini)\n",
+    "ranks = results_gemini_tab[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time! from Deepseek\n",
+    "\n",
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "response = deepseek.chat.completions.create(\n",
+    "    model=\"deepseek-chat\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results_deepseek = response.choices[0].message.content\n",
+    "print(results_deepseek)\n",
+    "\n",
+    "results_deepseek_tab = json.loads(results_deepseek)\n",
+    "ranks = results_deepseek_tab[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time! from Groq did not work as tokens per minute requested exceeded limit (Requested ~27K, Limit 8K)\n",
+    "# Entire section commented out.\n",
+    "\n",
+    "#groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "#response = groq.chat.completions.create(\n",
+    "#    model=\"openai/gpt-oss-120b\",\n",
+    "#    messages=judge_messages,\n",
+    "#)\n",
+    "#results_groq = response.choices[0].message.content\n",
+    "#print(results_groq)\n",
+    "\n",
+    "#results_groq_tab = json.loads(results_groq)\n",
+    "#ranks = results_groq_tab[\"results\"]\n",
+    "#for index, result in enumerate(ranks):\n",
+    "#    competitor = competitors[int(result)-1]\n",
+    "#    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from openai import OpenAI\n",
+    "\n",
+    "#Store each model's rankings\n",
+    "rankings = {\n",
+    "    \"openai-gpt-5-mini\": [\"claude-sonnet-4-5\", \"openai/gpt-oss-120b\", \"gpt-5-nano\", \"gemini-2.5-flash\", \"deepseek-chat\", \"llama3.2\"],\n",
+    "    \"claude-sonnet-4-5\": [\"gpt-5-nano\", \"claude-sonnet-4-5\", \"openai/gpt-oss-120b\", \"deepseek-chat\", \"gemini-2.5-flash\", \"llama3.2\"],\n",
+    "    \"gemini-2.5-flash\": [\"openai/gpt-oss-120b\", \"gemini-2.5-flash\", \"gpt-5-nano\", \"deepseek-chat\", \"claude-sonnet-4-5\", \"llama3.2\"],\n",
+    "    \"deepseek-chat\": [\"openai/gpt-oss-120b\", \"gemini-2.5-flash\", \"gpt-5-nano\", \"deepseek-chat\", \"claude-sonnet-4-5\", \"llama3.2\"]\n",
+    "}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Compute average rank per model\n",
+    "scores = {}\n",
+    "for model_name in rankings[list(rankings.keys())[0]]:  # iterate over unique models\n",
+    "    total_rank = 0\n",
+    "    for judge, ranks in rankings.items():\n",
+    "        total_rank += ranks.index(model_name) + 1  # ranks start at 1\n",
+    "    scores[model_name] = total_rank / len(rankings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Sort by average rank\n",
+    "sorted_scores = sorted(scores.items(), key=lambda x: x[1])\n",
+    "\n",
+    "print(\"\\n📊 Average Rank Results:\")\n",
+    "for i, (model, avg_rank) in enumerate(sorted_scores, 1):\n",
+    "    print(f\"{i}. {model} — Average Rank: {avg_rank:.2f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Prepare data for LLM evaluation\n",
+    "summary_prompt = f\"\"\"\n",
+    "We collected ranking data from multiple LLMs judging each other. \n",
+    "Here are the average ranks (lower is better):\n",
+    "\n",
+    "{json.dumps(scores, indent=2)}\n",
+    "\n",
+    "Please:\n",
+    "1. Provide a fairness-adjusted score (1–10) for each model.\n",
+    "2. Identify which model appears most consistent or robust across judges.\n",
+    "3. Summarize in 3 concise bullet points why the top model stands out.\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Send to an Chat GPT-5 for reasoning\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=[\n",
+    "        {\"role\": \"system\", \"content\": \"You are a neutral AI judge analyzing LLM ranking consistency.\"},\n",
+    "        {\"role\": \"user\", \"content\": summary_prompt}\n",
+    "    ])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Display the analysis\n",
+    "print(\"\\n🤖 LLM Evaluation Summary:\\n\")\n",
+    "print(response.choices[0].message.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_exercise.ipynb

@@ -0,0 +1,336 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# From Judging to Synthesizing — Evolving Multi-Agent Patterns\n",
+    "\n",
+    "In the original 2_lab2.ipynb, we explored a powerful agentic design pattern: sending the same question to multiple large language models (LLMs), then using a separate “judge” agent to evaluate and rank their responses. This approach is valuable for identifying the single best answer among many, leveraging the strengths of ensemble reasoning and critical evaluation.\n",
+    "\n",
+    "However, selecting just one “winner” can leave valuable insights from other models untapped. To address this, I am shifting to a new agentic pattern in this notebook: the synthesizer/improver pattern. Instead of merely ranking responses, we will prompt a dedicated LLM to review all answers, extract the most compelling ideas from each, and synthesize them into a single, improved response. \n",
+    "\n",
+    "This approach aims to combine the collective intelligence of multiple models, producing an answer that is richer, more nuanced, and more robust than any individual response.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their collective intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "teammates = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "teammates.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "teammates.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "teammates.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "teammates.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "teammates.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(teammates)\n",
+    "print(answers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for teammate, answer in zip(teammates, answers):\n",
+    "    print(f\"Teammate: {teammate}\\n\\n{answer}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from teammate {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "formatter = f\"\"\"You are taking the nost interesting ideas fron  {len(teammates)} teammates.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, select the most relevant ideas and make a report, including a title, subtitles to separate sections, and quoting the LLM providing the idea.\n",
+    "From that, you will create a new improved answer.\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(formatter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "formatter_messages = [{\"role\": \"user\", \"content\": formatter}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=formatter_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "display(Markdown(results))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_exercise_BrettSanders_ChainOfThought.ipynb

@@ -0,0 +1,241 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "# Lab 2 Exercise - Extending the Patterns\n",
+    "\n",
+    "This notebook extends the original lab by adding the Chain of Thought pattern to enhance the evaluation process.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import required packages\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load environment variables\n",
+    "load_dotenv(override=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize API clients\n",
+    "openai = OpenAI()\n",
+    "claude = Anthropic()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Original question generation\n",
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get responses from multiple models\n",
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]\n",
+    "\n",
+    "# OpenAI\n",
+    "response = openai.chat.completions.create(model=\"gpt-4o-mini\", messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "competitors.append(\"gpt-4o-mini\")\n",
+    "answers.append(answer)\n",
+    "display(Markdown(answer))\n",
+    "\n",
+    "# Claude\n",
+    "response = claude.messages.create(model=\"claude-3-7-sonnet-latest\", messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "competitors.append(\"claude-3-7-sonnet-latest\")\n",
+    "answers.append(answer)\n",
+    "display(Markdown(answer))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# NEW: Chain of Thought Evaluation\n",
+    "# First, let's create a detailed evaluation prompt that encourages step-by-step reasoning\n",
+    "\n",
+    "evaluation_prompt = f\"\"\"You are an expert evaluator of AI responses. Your task is to analyze and rank the following responses to this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Please follow these steps in your evaluation:\n",
+    "\n",
+    "1. For each response:\n",
+    "   - Identify the main arguments presented\n",
+    "   - Evaluate the clarity and coherence of the reasoning\n",
+    "   - Assess the depth and breadth of the analysis\n",
+    "   - Note any unique insights or perspectives\n",
+    "\n",
+    "2. Compare the responses:\n",
+    "   - How do they differ in their approach?\n",
+    "   - Which response demonstrates the most sophisticated understanding?\n",
+    "   - Which response provides the most practical and actionable insights?\n",
+    "\n",
+    "3. Provide your final ranking with detailed justification for each position.\n",
+    "\n",
+    "Here are the responses:\n",
+    "\n",
+    "{'\\\\n\\\\n'.join([f'Response {i+1} ({competitors[i]}):\\\\n{answer}' for i, answer in enumerate(answers)])}\n",
+    "\n",
+    "Please provide your evaluation in JSON format with the following structure:\n",
+    "{{\n",
+    "    \"detailed_analysis\": [\n",
+    "        {{\"competitor\": \"name\", \"strengths\": [], \"weaknesses\": [], \"unique_aspects\": []}},\n",
+    "        ...\n",
+    "    ],\n",
+    "    \"comparative_analysis\": \"detailed comparison of responses\",\n",
+    "    \"final_ranking\": [\"ranked competitor numbers\"],\n",
+    "    \"justification\": \"detailed explanation of the ranking\"\n",
+    "}}\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get the detailed evaluation\n",
+    "evaluation_messages = [{\"role\": \"user\", \"content\": evaluation_prompt}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=evaluation_messages,\n",
+    ")\n",
+    "detailed_evaluation = response.choices[0].message.content\n",
+    "print(detailed_evaluation)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Parse and display the results in a more readable format\n",
+    "\n",
+    "# Clean up the JSON string by removing markdown code block markers\n",
+    "json_str = detailed_evaluation.replace(\"```json\", \"\").replace(\"```\", \"\").strip()\n",
+    "\n",
+    "evaluation_dict = json.loads(json_str)\n",
+    "\n",
+    "print(\"Detailed Analysis:\")\n",
+    "for analysis in evaluation_dict[\"detailed_analysis\"]:\n",
+    "    print(f\"\\nCompetitor: {analysis['competitor']}\")\n",
+    "    print(\"Strengths:\")\n",
+    "    for strength in analysis['strengths']:\n",
+    "        print(f\"- {strength}\")\n",
+    "    print(\"\\nWeaknesses:\")\n",
+    "    for weakness in analysis['weaknesses']:\n",
+    "        print(f\"- {weakness}\")\n",
+    "    print(\"\\nUnique Aspects:\")\n",
+    "    for aspect in analysis['unique_aspects']:\n",
+    "        print(f\"- {aspect}\")\n",
+    "\n",
+    "print(\"\\nComparative Analysis:\")\n",
+    "print(evaluation_dict[\"comparative_analysis\"])\n",
+    "\n",
+    "print(\"\\nFinal Ranking:\")\n",
+    "for i, rank in enumerate(evaluation_dict[\"final_ranking\"]):\n",
+    "    print(f\"{i+1}. {competitors[int(rank)-1]}\")\n",
+    "\n",
+    "print(\"\\nJustification:\")\n",
+    "print(evaluation_dict[\"justification\"])\n"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "## Pattern Analysis\n",
+    "\n",
+    "This enhanced version uses several agentic design patterns:\n",
+    "\n",
+    "1. **Multi-agent Collaboration**: Sending the same question to multiple LLMs\n",
+    "2. **Evaluation/Judgment Pattern**: Using one LLM to evaluate responses from others\n",
+    "3. **Parallel Processing**: Running multiple models simultaneously\n",
+    "4. **Chain of Thought**: Added a structured, step-by-step evaluation process that breaks down the analysis into clear stages\n",
+    "\n",
+    "The Chain of Thought pattern is particularly valuable here because it:\n",
+    "- Forces the evaluator to consider multiple aspects of each response\n",
+    "- Provides more detailed and structured feedback\n",
+    "- Makes the evaluation process more transparent and explainable\n",
+    "- Helps identify specific strengths and weaknesses in each response\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_llm_reviewer.ipynb

@@ -0,0 +1,627 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This notebook extends the original by adding a reviewer pattern to evaluate the impact on model performance.\n",
+    "\n",
+    "In the new workflow, each model's answer is provided to a \"reviewer LLM\" who is prompted to \"Evaluate the response for clarity and strength of argument, and provide constructive suggestions for improving the answer.\" Each model is then given the chance to revise its answer based on the feedback but is also told, \"You are not required to take any of the feedback into account, but you want to win the competition.\"\n",
+    "\n",
+    "<table>\n",
+    "  <caption style=\"font-size: 1.2em; margin-bottom: 10px;\"><strong>Results for Representative Run</strong></caption>\n",
+    "  <thead>\n",
+    "    <tr>\n",
+    "      <th>Model</th>\n",
+    "      <th>Original Rank</th>\n",
+    "      <th>Exclusive Feedback</th>\n",
+    "      <th>With Feedback (all models)</th>\n",
+    "    </tr>\n",
+    "  </thead>\n",
+    "  <tbody>\n",
+    "    <tr>\n",
+    "      <td>gpt-4o-mini</td>\n",
+    "      <td>2</td>\n",
+    "      <td>3</td>\n",
+    "      <td>4</td>\n",
+    "    </tr>\n",
+    "    <tr>\n",
+    "      <td>claude-3-7-sonnet-latest</td>\n",
+    "      <td>6</td>\n",
+    "      <td>1</td>\n",
+    "      <td>1</td>\n",
+    "    </tr>\n",
+    "    <tr>\n",
+    "      <td>gemini-2.0-flash</td>\n",
+    "      <td>1</td>\n",
+    "      <td>1</td>\n",
+    "      <td>2</td>\n",
+    "    </tr>\n",
+    "    <tr>\n",
+    "      <td>deepseek-chat</td>\n",
+    "      <td>3</td>\n",
+    "      <td>2</td>\n",
+    "      <td>3</td>\n",
+    "    </tr>\n",
+    "    <tr>\n",
+    "      <td>llama-3.3-70b-versatile</td>\n",
+    "      <td>4</td>\n",
+    "      <td>3</td>\n",
+    "      <td>5</td>\n",
+    "    </tr>\n",
+    "    <tr>\n",
+    "      <td>llama3.2</td>\n",
+    "      <td>5</td>\n",
+    "      <td>4</td>\n",
+    "      <td>6</td>\n",
+    "    </tr>\n",
+    "  </tbody>\n",
+    "</table>\n",
+    "\n",
+    "The workflow is obviously non-deterministic and the results can vary greatly from run to run, but the introduction of a reviewer appeared to have a generaly positive impact on performance.  The table above shows the results for a representative run. It compares each model's rank versus the other models when it exclusively received feedback.  The table also shows the ranking when ALL models received feedback.  Exclusive use of feedback improved a model's ranking for five out of six models and decreased it for one model.\n",
+    "\n",
+    "Inspired by some other contributions, this worksheet also makes LLM calls asyncrhonously to reduce wait time."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "#!uv add prettytable\n",
+    "\n",
+    "import os\n",
+    "import asyncio\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI, AsyncOpenAI\n",
+    "from anthropic import AsyncAnthropic\n",
+    "from IPython.display import display\n",
+    "from pydantic import BaseModel, Field\n",
+    "from string import Template\n",
+    "from prettytable import PrettyTable\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class LLMResult(BaseModel):\n",
+    "    model: str\n",
+    "    answer: str\n",
+    "    feedback: str | None =Field(\n",
+    "        default = None, \n",
+    "        description=\"Mutable field.  This will be set by the reviewer.\")\n",
+    "    revised_answer: str | None =Field(\n",
+    "        default = None, \n",
+    "        description=\"Mutable field.  This will be set by the answerer after the reviewer has provided feedback.\")\n",
+    "    original_rank: int | None =Field(\n",
+    "        default = None, \n",
+    "        description=\"Mutable field.  Rank when no feedback is used by any models.\")\n",
+    "    exclusive_feedback: str | None =Field(\n",
+    "        default = None, \n",
+    "        description=\"Mutable field.  Rank when only this model used feedback.\")\n",
+    "    revised_rank: int | None =Field(\n",
+    "        default = None, \n",
+    "        description=\"Mutable field.  Rank when all models used feedback.\")\n",
+    "\n",
+    "results : list[LLMResult] = []\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "async def openai_answer(messages: list[dict[str, str]], model_name : str) -> str:\n",
+    "    openai = AsyncOpenAI()\n",
+    "    response = await openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "async def claude_anthropic_answer(messages: list[dict[str, str]], model_name : str) -> str:\n",
+    "    claude = AsyncAnthropic()\n",
+    "    response = await claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "    answer = response.content[0].text\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def gemini_google_answer(messages: list[dict[str, str]], model_name : str) -> str:     \n",
+    "    gemini = AsyncOpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "    response = await gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content.strip()\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def deepseek_answer(messages: list[dict[str, str]], model_name : str) -> str:\n",
+    "    deepseek = AsyncOpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "    response = await deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def groq_answer(messages: list[dict[str, str]], model_name : str) -> str:\n",
+    "    groq = AsyncOpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "    response = await groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def ollama_answer(messages: list[dict[str, str]], model_name : str) -> str:\n",
+    "    ollama = AsyncOpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "    response = await ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "    answer = response.choices[0].message.content\n",
+    "    print(f\"{model_name} answer: {answer[:50]}...\")\n",
+    "    return answer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "answerers  = [openai_answer, claude_anthropic_answer, gemini_google_answer, deepseek_answer, groq_answer, ollama_answer]\n",
+    "models = [\"gpt-4o-mini\", \"claude-3-7-sonnet-latest\", \"gemini-2.0-flash\", \"deepseek-chat\", \"llama-3.3-70b-versatile\", \"llama3.2\"]\n",
+    "\n",
+    "tasks = [ answerer(messages, model) for answerer, model in zip(answerers, models)]\n",
+    "answers : list[str] = await asyncio.gather(*tasks)\n",
+    "results : list[LLMResult] = [LLMResult(model=model, answer=answer) for model, answer in zip(models, answers)]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "answers "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "reviewer = f\"\"\"You are reviewing a submission for a writing competition.  The particpant has been given this question to answer:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate the response for clarity and strength of argument, and provide constructive suggestions for improving the answer.\n",
+    "Limit your feedback to 200 words.\n",
+    "\n",
+    "Here is the particpant's answer:\n",
+    "{{answer}}\n",
+    "\"\"\"\n",
+    "\n",
+    "async def review_answer(answer : str) -> str:\n",
+    "    openai = AsyncOpenAI()\n",
+    "    reviewer_messages = [{\"role\": \"user\", \"content\": reviewer.format(answer=answer)}]\n",
+    "    reviewer_response = await openai.chat.completions.create(\n",
+    "        model=\"gpt-4o-mini\",\n",
+    "        messages=reviewer_messages,\n",
+    "    )\n",
+    "    feedback = reviewer_response.choices[0].message.content\n",
+    "    print(f\"feedback: {feedback[:50]}...\")\n",
+    "    return feedback"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "\n",
+    "tasks = [review_answer(answer) for answer in answers]\n",
+    "feedback = await asyncio.gather(*tasks)\n",
+    "\n",
+    "for result, feedback in zip(results, feedback):\n",
+    "    result.feedback = feedback\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "revision_prompt = f\"\"\"You are revising a submission you wrote for a writing competition based on feedback from a reviewer.\n",
+    "\n",
+    "You are not required to take any of the feedback into account but you want to win the competition.\n",
+    "\n",
+    "The question was: \n",
+    "{question}\n",
+    "\n",
+    "The feedback was:\n",
+    "{{feedback}}\n",
+    "\n",
+    "And your original answer was:\n",
+    "{{answer}}\n",
+    "\n",
+    "Please return your revised answer and nothing else.\n",
+    "\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [{\"role\": \"user\", \"content\": revision_prompt.format(answer=answer, feedback=feedback)} for answer, feedback in zip(answers, feedback)]\n",
+    "tasks = [ answerer(messages, model) for answerer, model in zip(answerers, models)]\n",
+    "revised_answers = await asyncio.gather(*tasks)\n",
+    "\n",
+    "for revised_answer, result in zip(revised_answers, results):\n",
+    "    result.revised_answer = revised_answer\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# need to use Template because we are making a later substitution for \"together\"\n",
+    "judge = Template(f\"\"\"You are judging a competition between {len(results)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "$together\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\")\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def come_together(results : list[LLMResult], revised_entry : int | None ) -> list[dict[str, str]]:\n",
+    "    # include revised results for \"revised_entry\" or all entries if revise_entrys is None\n",
+    "    together = \"\"\n",
+    "    for index, result in enumerate(results):\n",
+    "        together += f\"# Response from competitor {index}\\n\\n\"\n",
+    "        together += result.answer if (index != revised_entry and revised_entry is not None) else result.revised_answer + \"\\n\\n\"\n",
+    "    return [{\"role\": \"user\", \"content\": judge.substitute(together=together)}]\n",
+    "\n",
+    "\n",
+    "# Judgement time!\n",
+    "async def judgement_time(results : list[LLMResult], revised_entry : int ) -> str:\n",
+    "    judge_messages = come_together(results, revised_entry)\n",
+    "\n",
+    "    openai = AsyncOpenAI()\n",
+    "    response = await openai.chat.completions.create(\n",
+    "        model=\"o3-mini\",\n",
+    "        messages=judge_messages,\n",
+    "    )\n",
+    "    results = response.choices[0].message.content\n",
+    "    results_dict = json.loads(results)\n",
+    "    results = {  int(model) : int(rank) +1 for rank, model in enumerate(results_dict[\"results\"]) }\n",
+    "    return results\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#evaluate the impact of feedback on model performance\n",
+    "\n",
+    "no_feedback = await judgement_time(results, -1)\n",
+    "with_feedback = await judgement_time(results, None)\n",
+    "\n",
+    "tasks = [ judgement_time(results, i) for i in range(len(results))]\n",
+    "model_spefic_feedback = await asyncio.gather(*tasks)\n",
+    "\n",
+    "for index, result in enumerate(results):\n",
+    "    result.original_rank = no_feedback[index]\n",
+    "    result.exclusive_feedback = model_spefic_feedback[index][index]\n",
+    "    result.revised_rank = with_feedback[index]\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "table = PrettyTable()\n",
+    "table.field_names = [\"Model\", \"Original Rank\", \"Exclusive Feedback\", \"With Feedback (all models)\"]\n",
+    "\n",
+    "for result in results:\n",
+    "    table.add_row([result.model, result.original_rank, result.exclusive_feedback, result.revised_rank])\n",
+    "\n",
+    "print(table)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_moneek.ipynb

@@ -0,0 +1,173 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "This program uses Evaluator Optimizer pattern to enhance generator's response in creating marketing content for smart keyboard."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Provide a short marketing content for XYZ keyboard. \"\n",
+    "request += \"It should be eagaging and talks about innovative features.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "marketing_statement= response.choices[0].message.content\n",
+    "print(marketing_statement)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"### Instruction ###\n",
+    "You are an expert tech gadget analyst. Your task is to evaluate a marketing material based on several criteria.\n",
+    "Please be brief.\n",
+    "\n",
+    "### Ad to Evaluate ###\n",
+    "{marketing_statement}\n",
+    "\n",
+    "### Evaluation Criteria ###\n",
+    "Evaluate the statement based on how engaging it is.\n",
+    "\n",
+    "### Expected Output Format ###\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": {{\"statement\": \"{marketing_statement}\", \"engagability\": \"Comment on whether the content is engaging\", \"critique\": \"Offer a specific critique and suggest at least one way the recipe could be improved\", \"verdict\": \"This should have a value either 'accepted' or 'rejected' based on whether the statement requires improvement\"}}}}\n",
+    "\"\"\"\n",
+    "\n",
+    "print(judge)\n",
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=judge_messages, max_tokens=1000)\n",
+    "marketing_statement_feedback = response.content[0].text\n",
+    "\n",
+    "print(marketing_statement_feedback)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results_dict = json.loads(marketing_statement_feedback)\n",
+    "feedback = results_dict[\"results\"]\n",
+    "print(feedback)\n",
+    "print(\"\\n\\n\")\n",
+    "display(Markdown(marketing_statement_feedback))\n",
+    "\n",
+    "print(f\"Marketing statement:\\n{feedback[\"statement\"]}\")\n",
+    "for key in feedback:\n",
+    "    if key == \"verdict\":\n",
+    "        if feedback[key] == \"accepted\":\n",
+    "            print(\"Marketing statement was accepted.\")\n",
+    "            break\n",
+    "        else:\n",
+    "            print(\"Marketing statement was rejected and requires revision. Please iterate over to call Generator and Evaluator for improvement\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_multi-evaluation-criteria.ipynb

@@ -0,0 +1,506 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-sonnet-4-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    display(Markdown(f\"# Competitor: {competitor}\\n\\n{answer}\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "evaluation_criteria = [\"Effectiveness in resolving the conflict\", \"Clarity of argument\", \"Creativity of solution\", \"Strength of argument\", \"conciseness\", \"applicability to a business context\"]\n",
+    "\n",
+    "judgements = []\n",
+    "\n",
+    "for evaluation_criterion in evaluation_criteria:\n",
+    "\n",
+    "  judgements.append (f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "  Each model has been given this question:\n",
+    "\n",
+    "  {question}\n",
+    "\n",
+    "  Your job is to evaluate each response for {evaluation_criterion}, and rank them in order of best to worst.\n",
+    "  Respond with JSON, and only JSON, with the following format:\n",
+    "  {{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "  Here are the responses from each competitor:\n",
+    "\n",
+    "  {together}\n",
+    "\n",
+    "  Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judgements[1])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "judge_messages = []\n",
+    "for judgement in judgements:\n",
+    "    judge_messages.append ([{\"role\": \"user\", \"content\": judgement}])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = []\n",
+    "# Judgement time!\n",
+    "for judge_message in judge_messages:\n",
+    "  openai = OpenAI()\n",
+    "  response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_message,\n",
+    "  )\n",
+    "  results.append (response.choices[0].message.content)\n",
+    "  print(results[0])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for result in results:\n",
+    "  print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "for result, evaluation_criterion in zip(results, evaluation_criteria):\n",
+    "    results_dict = json.loads(result)\n",
+    "    ranks = results_dict[\"results\"]\n",
+    "    display(Markdown(f\"### {evaluation_criterion}\"))\n",
+    "    for index, result in enumerate(ranks):\n",
+    "        competitor = competitors[int(result)-1]    \n",
+    "        display(Markdown(f\"Rank {index+1}: {competitor}\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_orchestrator.ipynb

@@ -0,0 +1,494 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ed27526e",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d3a7c44",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca5dc982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a53039f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a2f091d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Generate a challenging question\n",
+    "\n",
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(f\"Generated Question: {question}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6db23f57",
+   "metadata": {},
+   "source": [
+    "## Intelligent Orchestrator Pattern\n",
+    "\n",
+    "This pattern combines:\n",
+    "1. **Orchestrator-Workers** - Breaking down complex tasks\n",
+    "2. **Intelligent Routing** - Matching models to their strengths\n",
+    "3. **Synthesis** - Combining specialized responses"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7659a40a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 1: Orchestrator breaks down the question and assigns models based on their strengths\n",
+    "\n",
+    "orchestrator_prompt = f\"\"\"You are an intelligent orchestrator AI. Analyze this complex question and:\n",
+    "\n",
+    "1. Break it down into 3-4 simpler sub-questions\n",
+    "2. For each sub-question, recommend which type of AI model would be best suited\n",
+    "\n",
+    "Available models and their strengths:\n",
+    "- gpt-5-nano: Excellent at reasoning, complex logic, and nuanced analysis\n",
+    "- claude-sonnet-4-5: Strong at creative writing, empathy, and ethical reasoning\n",
+    "- gemini-2.5-flash: Fast at factual retrieval, technical explanations, and structured data\n",
+    "- deepseek-chat: Great at code generation, mathematical problems, and technical documentation\n",
+    "- openai/gpt-oss-120b: Good general purpose, cost-effective for straightforward tasks\n",
+    "- llama3.2: Privacy-focused local model, good for sensitive data and general tasks\n",
+    "\n",
+    "Original question: {question}\n",
+    "\n",
+    "Respond with JSON only, in this format:\n",
+    "{{\n",
+    "    \"sub_questions\": [\n",
+    "        {{\n",
+    "            \"question\": \"the sub-question text\",\n",
+    "            \"reasoning\": \"why this model is best for this sub-question\",\n",
+    "            \"recommended_model\": \"model_name\"\n",
+    "        }},\n",
+    "        ...\n",
+    "    ]\n",
+    "}}\"\"\"\n",
+    "\n",
+    "orchestrator_messages = [{\"role\": \"user\", \"content\": orchestrator_prompt}]\n",
+    "\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=orchestrator_messages,\n",
+    ")\n",
+    "orchestration_plan = json.loads(response.choices[0].message.content)\n",
+    "\n",
+    "print(\"🎯 Orchestrator's Intelligent Routing Plan:\\n\")\n",
+    "for i, item in enumerate(orchestration_plan[\"sub_questions\"], 1):\n",
+    "    print(f\"{i}. SUB-QUESTION: {item['question']}\")\n",
+    "    print(f\"   📍 ASSIGNED TO: {item['recommended_model']}\")\n",
+    "    print(f\"   💡 REASONING: {item['reasoning']}\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d62e4fa8",
+   "metadata": {},
+   "source": [
+    "## For Ollama setup\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+`) and run `ollama serve`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2761338c",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35785614",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e28b68fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 2: Initialize all model clients\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "\n",
+    "# Map model names to their API clients\n",
+    "model_clients = {\n",
+    "    \"gpt-5-nano\": (\"openai\", openai),\n",
+    "    \"claude-sonnet-4-5\": (\"claude\", claude),\n",
+    "    \"gemini-2.5-flash\": (\"gemini\", gemini),\n",
+    "    \"deepseek-chat\": (\"deepseek\", deepseek),\n",
+    "    \"openai/gpt-oss-120b\": (\"groq\", groq),\n",
+    "    \"llama3.2\": (\"ollama\", ollama)\n",
+    "}\n",
+    "\n",
+    "print(\"✅ All model clients initialized\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54b9bce6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 3: Execute sub-questions with orchestrator's model recommendations\n",
+    "\n",
+    "sub_answers = {}\n",
+    "\n",
+    "for idx, item in enumerate(orchestration_plan[\"sub_questions\"], 1):\n",
+    "    sub_q = item[\"question\"]\n",
+    "    recommended_model = item[\"recommended_model\"]\n",
+    "    \n",
+    "    print(f\"\\n🤖 Task {idx}: Using {recommended_model}\")\n",
+    "    print(f\"📝 Question: {sub_q[:80]}...\")\n",
+    "    \n",
+    "    messages = [{\"role\": \"user\", \"content\": sub_q}]\n",
+    "    \n",
+    "    # Route to the appropriate client\n",
+    "    client_type, client = model_clients.get(recommended_model, (\"openai\", openai))\n",
+    "    \n",
+    "    try:\n",
+    "        if client_type == \"claude\":\n",
+    "            response = client.messages.create(\n",
+    "                model=recommended_model, \n",
+    "                messages=messages, \n",
+    "                max_tokens=800\n",
+    "            )\n",
+    "            answer = response.content[0].text\n",
+    "        else:\n",
+    "            response = client.chat.completions.create(\n",
+    "                model=recommended_model, \n",
+    "                messages=messages\n",
+    "            )\n",
+    "            answer = response.choices[0].message.content\n",
+    "        \n",
+    "        sub_answers[sub_q] = {\n",
+    "            \"model\": recommended_model,\n",
+    "            \"answer\": answer,\n",
+    "            \"reasoning\": item[\"reasoning\"]\n",
+    "        }\n",
+    "        print(f\"✅ Completed successfully\\n\")\n",
+    "        \n",
+    "    except Exception as e:\n",
+    "        print(f\"❌ Error with {recommended_model}: {str(e)}\")\n",
+    "        # Fallback to GPT-5-mini\n",
+    "        response = openai.chat.completions.create(\n",
+    "            model=\"gpt-5-mini\", \n",
+    "            messages=messages\n",
+    "        )\n",
+    "        answer = response.choices[0].message.content\n",
+    "        sub_answers[sub_q] = {\n",
+    "            \"model\": \"gpt-5-mini (fallback)\",\n",
+    "            \"answer\": answer,\n",
+    "            \"reasoning\": \"Fallback due to error\"\n",
+    "        }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfe99aba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Display the sub-answers\n",
+    "\n",
+    "for sub_q, data in sub_answers.items():\n",
+    "    display(Markdown(f\"### Sub-Question: {sub_q}\"))\n",
+    "    display(Markdown(f\"**Model Used:** {data['model']}\"))\n",
+    "    display(Markdown(f\"**Answer:** {data['answer']}\"))\n",
+    "    print(\"\\n\" + \"=\"*80 + \"\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff84289b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 4: Synthesis - Combine all specialized responses\n",
+    "\n",
+    "synthesis_prompt = f\"\"\"You are a synthesis AI combining specialized responses into a comprehensive answer.\n",
+    "\n",
+    "ORIGINAL QUESTION: {question}\n",
+    "\n",
+    "The orchestrator intelligently routed sub-questions to models based on their strengths:\n",
+    "\n",
+    "\"\"\"\n",
+    "\n",
+    "for sub_q, data in sub_answers.items():\n",
+    "    synthesis_prompt += f\"\\n{'='*60}\\n\"\n",
+    "    synthesis_prompt += f\"SUB-QUESTION: {sub_q}\\n\"\n",
+    "    synthesis_prompt += f\"ASSIGNED TO: {data['model']}\\n\"\n",
+    "    synthesis_prompt += f\"SELECTION REASONING: {data['reasoning']}\\n\"\n",
+    "    synthesis_prompt += f\"ANSWER: {data['answer']}\\n\"\n",
+    "\n",
+    "synthesis_prompt += f\"\\n{'='*60}\\n\"\n",
+    "synthesis_prompt += \"\\nSynthesize these specialized responses into one coherent, comprehensive answer to the original question.\"\n",
+    "synthesis_prompt += \"\\nHighlight how different model strengths contributed to the final answer.\"\n",
+    "\n",
+    "synthesis_messages = [{\"role\": \"user\", \"content\": synthesis_prompt}]\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-nano\",\n",
+    "    messages=synthesis_messages,\n",
+    ")\n",
+    "synthesized_answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(\"## 🎯 Intelligently Orchestrated & Synthesized Answer:\"))\n",
+    "display(Markdown(synthesized_answer))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5191a58a",
+   "metadata": {},
+   "source": [
+    "## Pattern Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fa0de4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Display pattern analysis\n",
+    "\n",
+    "model_list = '\\n'.join(f'- **{data[\"model\"]}**: {data[\"reasoning\"]}' for data in sub_answers.values())\n",
+    "\n",
+    "analysis = f\"\"\"\n",
+    "## 📊 Pattern Analysis\n",
+    "\n",
+    "### Patterns Used from Anthropic's Building Effective Agents:\n",
+    "\n",
+    "1. **Orchestrator-Workers Pattern** ✅\n",
+    "   - One LLM coordinates the workflow\n",
+    "   - Breaks complex tasks into subtasks\n",
+    "   - Distributes work to specialized workers\n",
+    "   - Synthesizes results into coherent output\n",
+    "\n",
+    "2. **Intelligent Routing Pattern** ✅\n",
+    "   - Matches models to their specific strengths\n",
+    "   - Dynamic model selection based on task requirements\n",
+    "   - Optimizes for quality by leveraging specialization\n",
+    "\n",
+    "3. **Implicit Parallelization** ⚡\n",
+    "   - Sub-questions can be executed in parallel\n",
+    "   - Independent tasks distributed across models\n",
+    "\n",
+    "### Key Innovations:\n",
+    "\n",
+    "**Capability-Aware Orchestration**: This is more sophisticated than simple task distribution. \n",
+    "The orchestrator:\n",
+    "- Understands each model's strengths and weaknesses\n",
+    "- Makes intelligent routing decisions\n",
+    "- Documents its reasoning for transparency\n",
+    "- Enables cost optimization (expensive models only where needed)\n",
+    "\n",
+    "### Models Used in This Run:\n",
+    "{model_list}\n",
+    "\n",
+    "### Total API Calls:\n",
+    "- 1 orchestrator call (question decomposition)\n",
+    "- {len(sub_answers)} worker calls (sub-question answering)\n",
+    "- 1 synthesizer call (final answer composition)\n",
+    "- **Total: {len(sub_answers) + 2} API calls**\n",
+    "\"\"\"\n",
+    "\n",
+    "display(Markdown(analysis))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3434b0a7",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Try modifying the orchestrator prompt to include cost considerations. Add a 'budget' field for each model and have the orchestrator balance quality vs. cost when making routing decisions.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0168301c",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">The Intelligent Orchestrator pattern is critical for production systems where:\n",
+    "            <ul>\n",
+    "                <li><b>Cost optimization</b> matters - use expensive models only where their strengths are needed</li>\n",
+    "                <li><b>Quality is paramount</b> - leverage specialization for each aspect of complex tasks</li>\n",
+    "                <li><b>Scalability is required</b> - easily add new models and define their capabilities</li>\n",
+    "                <li><b>Transparency is valued</b> - document routing decisions and reasoning</li>\n",
+    "            </ul>\n",
+    "            This pattern mirrors how you'd assemble a team of specialists for a complex project, making it intuitive for business stakeholders to understand.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "agents",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

community_contributions/2_lab2_perplexity_support.ipynb

@@ -0,0 +1,497 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Welcome to the Second Lab - Week 1, Day 3\n",
+    "\n",
+    "Today we will work with lots of models! This is a way to get comfortable with APIs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Important point - please read</h2>\n",
+    "            <span style=\"color:#ff7800;\">The way I collaborate with you may be different to other courses you've taken. I prefer not to type code while you watch. Rather, I execute Jupyter Labs, like this, and give you an intuition for what's going on. My suggestion is that you carefully execute this yourself, <b>after</b> watching the lecture. Add print statements to understand what's going on, and then come up with your own variations.<br/><br/>If you have time, I'd love it if you submit a PR for changes in the community_contributions folder - instructions in the resources. Also, if you have a Github account, use this to showcase your variations. Not only is this essential practice, but it demonstrates your skills to others, including perhaps future clients or employers...\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Start with imports - ask ChatGPT to explain any package that you don't know\n",
+    "\n",
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from anthropic import Anthropic\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Always remember to do this!\n",
+    "load_dotenv(override=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Print the key prefixes to help with any debugging\n",
+    "\n",
+    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
+    "anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')\n",
+    "google_api_key = os.getenv('GOOGLE_API_KEY')\n",
+    "deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')\n",
+    "groq_api_key = os.getenv('GROQ_API_KEY')\n",
+    "perplexity_api_key = os.getenv('PERPLEXITY_API_KEY')\n",
+    "\n",
+    "if openai_api_key:\n",
+    "    print(f\"OpenAI API Key exists and begins {openai_api_key[:8]}\")\n",
+    "else:\n",
+    "    print(\"OpenAI API Key not set\")\n",
+    "    \n",
+    "if anthropic_api_key:\n",
+    "    print(f\"Anthropic API Key exists and begins {anthropic_api_key[:7]}\")\n",
+    "else:\n",
+    "    print(\"Anthropic API Key not set (and this is optional)\")\n",
+    "\n",
+    "if google_api_key:\n",
+    "    print(f\"Google API Key exists and begins {google_api_key[:2]}\")\n",
+    "else:\n",
+    "    print(\"Google API Key not set (and this is optional)\")\n",
+    "\n",
+    "if deepseek_api_key:\n",
+    "    print(f\"DeepSeek API Key exists and begins {deepseek_api_key[:3]}\")\n",
+    "else:\n",
+    "    print(\"DeepSeek API Key not set (and this is optional)\")\n",
+    "\n",
+    "if groq_api_key:\n",
+    "    print(f\"Groq API Key exists and begins {groq_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Groq API Key not set (and this is optional)\")\n",
+    "\n",
+    "if perplexity_api_key:\n",
+    "    print(f\"Perplexity API Key exists and begins {perplexity_api_key[:4]}\")\n",
+    "else:\n",
+    "    print(\"Perplexity API Key not set (and this is optional)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to evaluate their intelligence. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The API we know well\n",
+    "\n",
+    "model_name = \"gpt-4o-mini\"\n",
+    "\n",
+    "response = openai.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Anthropic has a slightly different API, and Max Tokens is required\n",
+    "\n",
+    "model_name = \"claude-3-7-sonnet-latest\"\n",
+    "\n",
+    "claude = Anthropic()\n",
+    "response = claude.messages.create(model=model_name, messages=messages, max_tokens=1000)\n",
+    "answer = response.content[0].text\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.0-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "deepseek = OpenAI(api_key=deepseek_api_key, base_url=\"https://api.deepseek.com/v1\")\n",
+    "model_name = \"deepseek-chat\"\n",
+    "\n",
+    "response = deepseek.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groq = OpenAI(api_key=groq_api_key, base_url=\"https://api.groq.com/openai/v1\")\n",
+    "model_name = \"llama-3.3-70b-versatile\"\n",
+    "\n",
+    "response = groq.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "perplexity = OpenAI(api_key=perplexity_api_key, base_url=\"https://api.perplexity.ai\")\n",
+    "model_name = \"sonar\"\n",
+    "\n",
+    "response = perplexity.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For the next cell, we will use Ollama\n",
+    "\n",
+    "Ollama runs a local web service that gives an OpenAI compatible endpoint,  \n",
+    "and runs models locally using high performance C++ code.\n",
+    "\n",
+    "If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.\n",
+    "\n",
+    "After it's installed, you should be able to visit here: http://localhost:11434 and see the message \"Ollama is running\"\n",
+    "\n",
+    "You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+\\`) and run `ollama serve`\n",
+    "\n",
+    "Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):\n",
+    "\n",
+    "`ollama pull <model_name>` downloads a model locally  \n",
+    "`ollama ls` lists all the models you've downloaded  \n",
+    "`ollama rm <model_name>` deletes the specified model from your downloads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/stop.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Super important - ignore me at your peril!</h2>\n",
+    "            <span style=\"color:#ff7800;\">The model called <b>llama3.3</b> is FAR too large for home computers - it's not intended for personal computing and will consume all your resources! Stick with the nicely sized <b>llama3.2</b> or <b>llama3.2:1b</b> and if you want larger, try llama3.1 or smaller variants of Qwen, Gemma, Phi or DeepSeek. See the <A href=\"https://ollama.com/models\">the Ollama models page</a> for a full list of models and sizes.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!ollama pull llama3.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')\n",
+    "model_name = \"llama3.2\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# So where are we?\n",
+    "\n",
+    "print(competitors)\n",
+    "print(answers)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"o3-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/exercise.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#ff7800;\">Exercise</h2>\n",
+    "            <span style=\"color:#ff7800;\">Which pattern(s) did this use? Try updating this to add another Agentic design pattern.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<table style=\"margin: 0; text-align: left; width:100%\">\n",
+    "    <tr>\n",
+    "        <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n",
+    "            <img src=\"../assets/business.png\" width=\"150\" height=\"150\" style=\"display: block;\" />\n",
+    "        </td>\n",
+    "        <td>\n",
+    "            <h2 style=\"color:#00bfff;\">Commercial implications</h2>\n",
+    "            <span style=\"color:#00bfff;\">These kinds of patterns - to send a task to multiple models, and evaluate results,\n",
+    "            are common where you need to improve the quality of your LLM response. This approach can be universally applied\n",
+    "            to business projects where accuracy is critical.\n",
+    "            </span>\n",
+    "        </td>\n",
+    "    </tr>\n",
+    "</table>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

community_contributions/2_lab2_qualitycode_review.ipynb

@@ -0,0 +1,320 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4226f6f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "from IPython.display import Markdown, display"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4cdb4a69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)\n",
+    "\n",
+    "openai_api_key = os.getenv(\"OPENAI_API_KEY\")\n",
+    "google_api_key = os.getenv(\"GOOGLE_API_KEY\")\n",
+    "\n",
+    "if openai_api_key is None:\n",
+    "    raise ValueError(\"OPENAI_API_KEY is not set\")\n",
+    "\n",
+    "if google_api_key is None:\n",
+    "    raise ValueError(\"GOOGLE_API_KEY is not set\")\n",
+    "\n",
+    "\n",
+    "\n",
+    "# The API we know well\n",
+    "# I've updated this with the latest model, but it can take some time because it likes to think!\n",
+    "# Replace the model with gpt-4.1-mini if you'd prefer not to wait 1-2 mins"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "31c74663",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "request = \"Please come up with a challenging, nuanced question that I can ask a number of LLMs to generate a code for algorithm like binary tree for live coding competition. \"\n",
+    "request += \"Answer only with the question, no explanation.\"\n",
+    "messages = [{\"role\": \"user\", \"content\": request}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0b9dc1d7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'role': 'user', 'content': 'Please come up with a challenging, nuanced question that I can ask a number of LLMs to generate a code for algorithm like binary tree for live coding competition. Answer only with the question, no explanation.'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "298de8ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "How would you implement a binary tree in Python that includes methods for insertion, deletion, traversal (in-order, pre-order, post-order), and searching for a specific value, while also ensuring balanced height after each insertion?\n"
+     ]
+    }
+   ],
+   "source": [
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-4o-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "question = response.choices[0].message.content\n",
+    "print(question)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b26c539a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "competitors = []\n",
+    "answers = []\n",
+    "messages = [{\"role\": \"user\", \"content\": question}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cdd1c225",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = \"gpt-5-mini\"\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=messages,\n",
+    ")\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "answers.append(answer)\n",
+    "competitors.append(model_name)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ad9ccdb4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gemini = OpenAI(api_key=google_api_key, base_url=\"https://generativelanguage.googleapis.com/v1beta/openai/\")\n",
+    "model_name = \"gemini-2.5-flash\"\n",
+    "\n",
+    "response = gemini.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14709041",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ollama = OpenAI(base_url=\"http://localhost:11434/v1\")\n",
+    "model_name = \"phi3:latest\"\n",
+    "\n",
+    "response = ollama.chat.completions.create(model=model_name, messages=messages)\n",
+    "answer = response.choices[0].message.content\n",
+    "\n",
+    "display(Markdown(answer))\n",
+    "competitors.append(model_name)\n",
+    "answers.append(answer)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dd5e23f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(competitors)\n",
+    "print(answers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "96a5c917",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# It's nice to know how to use \"zip\"\n",
+    "for competitor, answer in zip(competitors, answers):\n",
+    "    print(f\"Competitor: {competitor}\\n\\n{answer}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "4e71c1c5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Let's bring this together - note the use of \"enumerate\"\n",
+    "\n",
+    "together = \"\"\n",
+    "for index, answer in enumerate(answers):\n",
+    "    together += f\"# Response from competitor {index+1}\\n\\n\"\n",
+    "    together += answer + \"\\n\\n\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db4b67c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(together)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "dbf92ba2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge = f\"\"\"You are judging a competition between {len(competitors)} competitors.\n",
+    "Each model has been given this question:\n",
+    "\n",
+    "{question}\n",
+    "\n",
+    "Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.\n",
+    "Respond with JSON, and only JSON, with the following format:\n",
+    "{{\"results\": [\"best competitor number\", \"second best competitor number\", \"third best competitor number\", ...]}}\n",
+    "\n",
+    "Here are the responses from each competitor:\n",
+    "\n",
+    "{together}\n",
+    "\n",
+    "Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks.\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3eebf961",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(judge)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "5953feb5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "judge_messages = [{\"role\": \"user\", \"content\": judge}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bde0152",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Judgement time!\n",
+    "\n",
+    "openai = OpenAI()\n",
+    "response = openai.chat.completions.create(\n",
+    "    model=\"gpt-5-mini\",\n",
+    "    messages=judge_messages,\n",
+    ")\n",
+    "results = response.choices[0].message.content\n",
+    "print(results)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2c8f1410",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# OK let's turn this into results!\n",
+    "\n",
+    "results_dict = json.loads(results)\n",
+    "ranks = results_dict[\"results\"]\n",
+    "for index, result in enumerate(ranks):\n",
+    "    competitor = competitors[int(result)-1]\n",
+    "    print(f\"Rank {index+1}: {competitor}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e5e6f540",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}