| import gradio as gr |
| import json |
| import random |
| from datetime import datetime |
| import pandas as pd |
| import plotly.express as px |
| import plotly.graph_objects as go |
|
|
| |
| USERS_DB = {} |
| PROGRESS_DB = {} |
|
|
| |
| CURRICULUM = { |
| "beginner": { |
| "title": "AI Foundations to Agent Builder", |
| "duration": "80-100 hours", |
| "modules": [ |
| {"name": "Introduction to AI and Agents", "duration": "5 hours"}, |
| {"name": "Understanding Language Models", "duration": "8 hours"}, |
| {"name": "Basic Prompt Engineering", "duration": "10 hours"}, |
| {"name": "No-Code Agent Building", "duration": "15 hours"}, |
| {"name": "Business Applications", "duration": "12 hours"}, |
| {"name": "First Agent Project", "duration": "20 hours"}, |
| {"name": "Deployment Basics", "duration": "10 hours"}, |
| {"name": "Career Preparation", "duration": "10 hours"} |
| ] |
| }, |
| "intermediate": { |
| "title": "Agent Developer Professional", |
| "duration": "120-150 hours", |
| "modules": [ |
| {"name": "Advanced Prompt Engineering", "duration": "15 hours"}, |
| {"name": "Python for AI Agents", "duration": "20 hours"}, |
| {"name": "LangChain Fundamentals", "duration": "15 hours"}, |
| {"name": "Multi-Provider Integration", "duration": "20 hours"}, |
| {"name": "Memory and Context Management", "duration": "15 hours"}, |
| {"name": "Tool Creation and Integration", "duration": "20 hours"}, |
| {"name": "Production Deployment", "duration": "15 hours"}, |
| {"name": "Advanced Projects", "duration": "30 hours"} |
| ] |
| }, |
| "advanced": { |
| "title": "Enterprise AI Architect", |
| "duration": "180-220 hours", |
| "modules": [ |
| {"name": "Multi-Agent Systems Design", "duration": "25 hours"}, |
| {"name": "Custom Framework Development", "duration": "30 hours"}, |
| {"name": "Scalable Architecture Patterns", "duration": "20 hours"}, |
| {"name": "Security and Compliance", "duration": "15 hours"}, |
| {"name": "Performance Optimization", "duration": "20 hours"}, |
| {"name": "Industry Specialization", "duration": "30 hours"}, |
| {"name": "Enterprise Integration", "duration": "25 hours"}, |
| {"name": "Capstone Project", "duration": "35 hours"} |
| ] |
| } |
| } |
|
|
| |
| AGENT_TEMPLATES = { |
| "customer_service": { |
| "name": "Customer Service Pro", |
| "description": "Handle customer inquiries with empathy and efficiency", |
| "code": """# Customer Service Agent |
| agent = AgentBuilder( |
| name="CustomerServicePro", |
| model="gpt-4", |
| system_prompt=\"\"\"You are a helpful customer service agent. |
| Be empathetic, solution-focused, and professional. |
| Always try to resolve issues on first contact.\"\"\", |
| tools=["order_lookup", "refund_process", "ticket_create"], |
| memory_type="conversation", |
| max_tokens=150 |
| ) |
| |
| # Example usage |
| response = agent.process("I haven't received my order #12345") |
| print(response)""" |
| }, |
| "data_analyst": { |
| "name": "Data Analyst Agent", |
| "description": "Automated data analysis and visualization", |
| "code": """# Data Analysis Agent |
| analyst = DataAnalystAgent( |
| name="DataInsightsPro", |
| model="gpt-4", |
| capabilities={ |
| "data_sources": ["csv", "sql", "api"], |
| "analysis_types": ["descriptive", "predictive", "prescriptive"], |
| "visualizations": ["charts", "dashboards", "reports"] |
| }, |
| auto_insights=True |
| ) |
| |
| # Analyze sales data |
| insights = analyst.analyze("sales_data.csv", |
| questions=["What are the top performing products?", |
| "Identify seasonal trends", |
| "Predict next quarter revenue"])""" |
| }, |
| "content_creator": { |
| "name": "Content Creator Agent", |
| "description": "Generate engaging content for multiple platforms", |
| "code": """# Content Creation Agent |
| creator = ContentAgent( |
| name="ContentGenius", |
| model="claude-3-opus", |
| style_guide={ |
| "tone": "professional yet engaging", |
| "format": "SEO-optimized", |
| "platforms": ["blog", "social", "email"] |
| }, |
| fact_checking=True |
| ) |
| |
| # Generate blog post |
| post = creator.create( |
| type="blog_post", |
| topic="The Future of AI Agents", |
| keywords=["AI agents", "automation", "future of work"], |
| length=1000 |
| )""" |
| } |
| } |
|
|
| def create_header(): |
| return """ |
| <div style="text-align: center; padding: 20px;"> |
| <h1 style="color: #6366f1; font-size: 3em; margin-bottom: 10px;">🎓 AgenticAI Academy</h1> |
| <p style="font-size: 1.2em; color: #666;">Master AI Agent Development • From Beginner to Expert</p> |
| <p style="margin-top: 20px;"> |
| <span style="background: #e0f2fe; color: #0369a1; padding: 5px 15px; border-radius: 20px; margin: 0 5px;">$32B Market by 2030</span> |
| <span style="background: #fef3c7; color: #d97706; padding: 5px 15px; border-radius: 20px; margin: 0 5px;">31.2% Annual Growth</span> |
| <span style="background: #fce7f3; color: #be185d; padding: 5px 15px; border-radius: 20px; margin: 0 5px;">$100K-250K+ Salaries</span> |
| </p> |
| </div> |
| """ |
|
|
| def register_user(name, email, experience_level, learning_goal): |
| """Register a new user""" |
| if email in USERS_DB: |
| return "❌ Email already registered. Please login instead." |
| |
| USERS_DB[email] = { |
| "name": name, |
| "experience_level": experience_level, |
| "learning_goal": learning_goal, |
| "registered": datetime.now().isoformat(), |
| "path": "beginner" if experience_level == "No coding experience" else "intermediate" |
| } |
| |
| PROGRESS_DB[email] = { |
| "completed_modules": [], |
| "current_module": 0, |
| "total_hours": 0, |
| "projects": [] |
| } |
| |
| return f"✅ Welcome to AgenticAI Academy, {name}! Your {USERS_DB[email]['path']} learning path is ready." |
|
|
| def get_personalized_curriculum(email): |
| """Get personalized curriculum based on user profile""" |
| if email not in USERS_DB: |
| return "Please register first to see your personalized curriculum." |
| |
| user = USERS_DB[email] |
| path = user["path"] |
| curriculum = CURRICULUM[path] |
| |
| progress = PROGRESS_DB.get(email, {}) |
| completed = len(progress.get("completed_modules", [])) |
| |
| output = f"## 📚 Your Learning Path: {curriculum['title']}\n\n" |
| output += f"**Total Duration:** {curriculum['duration']}\n" |
| output += f"**Progress:** {completed}/{len(curriculum['modules'])} modules completed\n\n" |
| |
| output += "### Modules:\n" |
| for i, module in enumerate(curriculum['modules']): |
| status = "✅" if i < completed else "⏳" |
| output += f"{i+1}. {status} **{module['name']}** ({module['duration']})\n" |
| |
| return output |
|
|
| def generate_agent_code(agent_type, use_case, model_choice, include_memory, include_tools): |
| """Generate custom agent code based on parameters""" |
| template = AGENT_TEMPLATES.get(agent_type, AGENT_TEMPLATES["customer_service"]) |
| |
| code = f"""# Generated {agent_type.replace('_', ' ').title()} Agent |
| # Use case: {use_case} |
| |
| from agenticai import AgentBuilder, MemoryStore, ToolRegistry |
| |
| # Initialize agent |
| agent = AgentBuilder( |
| name="{agent_type}_agent", |
| model="{model_choice}", |
| temperature=0.7 |
| ) |
| |
| # Configure system prompt |
| agent.set_system_prompt(\"\"\" |
| {template['description']} |
| Specific use case: {use_case} |
| \"\"\") |
| """ |
| |
| if include_memory: |
| code += """ |
| # Add memory capabilities |
| agent.add_memory( |
| type="long_term", |
| store=MemoryStore( |
| vector_db="pinecone", |
| embedding_model="text-embedding-ada-002" |
| ) |
| ) |
| """ |
| |
| if include_tools: |
| code += """ |
| # Add tools |
| agent.add_tools([ |
| "web_search", |
| "calculator", |
| "code_executor", |
| "file_handler" |
| ]) |
| """ |
| |
| code += """ |
| # Example usage |
| response = agent.process("Your query here") |
| print(response) |
| |
| # Deploy agent |
| # agent.deploy(endpoint="/api/agent", port=8080) |
| """ |
| |
| return code |
|
|
| def create_progress_visualization(email): |
| """Create visual progress chart""" |
| if email not in PROGRESS_DB: |
| return None |
| |
| progress = PROGRESS_DB[email] |
| user = USERS_DB.get(email, {}) |
| path = user.get("path", "beginner") |
| curriculum = CURRICULUM[path] |
| |
| |
| modules = [m["name"] for m in curriculum["modules"]] |
| completed = progress.get("completed_modules", []) |
| status = ["Completed" if i < len(completed) else "Pending" for i in range(len(modules))] |
| hours = [m["duration"].split()[0] for m in curriculum["modules"]] |
| |
| |
| df = pd.DataFrame({ |
| "Module": modules, |
| "Status": status, |
| "Hours": [int(h) for h in hours] |
| }) |
| |
| |
| fig = px.bar(df, x="Hours", y="Module", orientation='h', color="Status", |
| color_discrete_map={"Completed": "#10b981", "Pending": "#e5e7eb"}, |
| title="Your Learning Progress") |
| |
| fig.update_layout( |
| showlegend=False, |
| xaxis_title="Duration (hours)", |
| yaxis_title="", |
| height=400 |
| ) |
| |
| return fig |
|
|
| def simulate_agent_conversation(agent_type, user_input): |
| """Simulate agent responses""" |
| responses = { |
| "customer_service": [ |
| "I understand your concern. Let me look into that for you right away.", |
| "I've found your order #12345. It's currently in transit and should arrive within 2 days.", |
| "I apologize for the inconvenience. I'm processing a full refund for you now.", |
| "Is there anything else I can help you with today?" |
| ], |
| "data_analyst": [ |
| "I've analyzed your data and found some interesting patterns.", |
| "The top performing category shows 34% growth month-over-month.", |
| "Based on historical trends, I predict a 15% increase in Q2.", |
| "I've created a visualization to better illustrate these insights." |
| ], |
| "content_creator": [ |
| "I've drafted an engaging blog post optimized for your keywords.", |
| "The content includes relevant statistics and expert insights.", |
| "I've structured it with SEO-friendly headers and meta descriptions.", |
| "Would you like me to adjust the tone or add more sections?" |
| ] |
| } |
| |
| |
| agent_responses = responses.get(agent_type, responses["customer_service"]) |
| response = random.choice(agent_responses) |
| |
| return f"**Agent Response:** {response}\n\n*This is a simulated response. In the full course, you'll build real agents that connect to actual AI models.*" |
|
|
| def create_market_stats(): |
| """Create market statistics visualization""" |
| |
| years = list(range(2024, 2031)) |
| market_size = [5.88, 7.73, 10.16, 13.36, 17.57, 23.11, 30.39] |
| |
| fig = go.Figure() |
| |
| fig.add_trace(go.Scatter( |
| x=years, |
| y=market_size, |
| mode='lines+markers', |
| name='Market Size', |
| line=dict(color='#6366f1', width=3), |
| marker=dict(size=8) |
| )) |
| |
| fig.update_layout( |
| title="AI Education Market Growth (Billions USD)", |
| xaxis_title="Year", |
| yaxis_title="Market Size (Billions)", |
| showlegend=False, |
| height=400 |
| ) |
| |
| return fig |
|
|
| |
| with gr.Blocks(title="AgenticAI Academy", theme=gr.themes.Base()) as app: |
| gr.HTML(create_header()) |
| |
| with gr.Tabs(): |
| |
| with gr.TabItem("🚀 Get Started"): |
| with gr.Row(): |
| with gr.Column(): |
| gr.Markdown(""" |
| ### Start Your AI Agent Development Journey |
| |
| Join thousands of professionals learning to build production-ready AI agents. |
| Our hands-on curriculum takes you from beginner to expert, with real projects |
| and industry certifications. |
| """) |
| |
| name_input = gr.Textbox(label="Full Name", placeholder="John Doe") |
| email_input = gr.Textbox(label="Email", placeholder="john@example.com") |
| experience_level = gr.Radio( |
| label="Current Experience Level", |
| choices=["No coding experience", "Some programming knowledge", "Experienced developer"], |
| value="No coding experience" |
| ) |
| learning_goal = gr.Dropdown( |
| label="Primary Learning Goal", |
| choices=[ |
| "Career transition to AI", |
| "Add AI skills to current role", |
| "Build AI products/startups", |
| "Enterprise AI implementation" |
| ], |
| value="Career transition to AI" |
| ) |
| |
| register_btn = gr.Button("Start Free Trial", variant="primary", size="lg") |
| registration_output = gr.Textbox(label="Registration Status", lines=2) |
| |
| with gr.Column(): |
| gr.Markdown(""" |
| ### 📊 Market Opportunity |
| |
| The AI education market is experiencing explosive growth, creating unprecedented |
| opportunities for skilled professionals. |
| """) |
| market_chart = gr.Plot(value=create_market_stats()) |
| |
| gr.Markdown(""" |
| ### 💰 Earning Potential |
| - **Freelance:** $50-500/hour |
| - **Full-time:** $100K-250K+ annually |
| - **Consulting:** $1,000-5,000/day |
| - **Products:** Unlimited scaling potential |
| """) |
| |
| register_btn.click( |
| register_user, |
| inputs=[name_input, email_input, experience_level, learning_goal], |
| outputs=registration_output |
| ) |
| |
| |
| with gr.TabItem("📚 Curriculum"): |
| with gr.Row(): |
| with gr.Column(scale=1): |
| curriculum_email = gr.Textbox( |
| label="Enter your email to see personalized curriculum", |
| placeholder="john@example.com" |
| ) |
| show_curriculum_btn = gr.Button("Show My Curriculum", variant="primary") |
| |
| with gr.Column(scale=2): |
| curriculum_output = gr.Markdown() |
| progress_chart = gr.Plot() |
| |
| show_curriculum_btn.click( |
| get_personalized_curriculum, |
| inputs=[curriculum_email], |
| outputs=curriculum_output |
| ).then( |
| create_progress_visualization, |
| inputs=[curriculum_email], |
| outputs=progress_chart |
| ) |
| |
| gr.Markdown(""" |
| ### 🎓 Available Learning Paths |
| |
| #### Beginner Path: AI Foundations to Agent Builder (80-100 hours) |
| Perfect for non-technical professionals. Learn to build AI agents using visual tools |
| and no-code platforms. Focus on business applications and practical implementation. |
| |
| #### Intermediate Path: Agent Developer Professional (120-150 hours) |
| For developers ready to add AI to their toolkit. Master Python-based agent development, |
| advanced prompt engineering, and multi-provider integration. |
| |
| #### Advanced Path: Enterprise AI Architect (180-220 hours) |
| Design and deploy complex multi-agent systems. Learn scalable architectures, |
| security best practices, and industry-specific solutions. |
| """) |
| |
| |
| with gr.TabItem("🔧 Agent Builder"): |
| gr.Markdown(""" |
| ### Build Your Custom AI Agent |
| |
| Use our code generator to create a starting template for your AI agent. |
| In the full course, you'll learn to build and deploy these agents with real AI models. |
| """) |
| |
| with gr.Row(): |
| with gr.Column(): |
| agent_type = gr.Dropdown( |
| label="Agent Type", |
| choices=["customer_service", "data_analyst", "content_creator"], |
| value="customer_service" |
| ) |
| use_case = gr.Textbox( |
| label="Specific Use Case", |
| placeholder="E.g., E-commerce support, Financial analysis, Blog writing" |
| ) |
| model_choice = gr.Dropdown( |
| label="AI Model", |
| choices=["gpt-4", "gpt-3.5-turbo", "claude-3-opus", "gemini-pro"], |
| value="gpt-4" |
| ) |
| include_memory = gr.Checkbox(label="Include Memory System", value=True) |
| include_tools = gr.Checkbox(label="Include External Tools", value=True) |
| |
| generate_btn = gr.Button("Generate Agent Code", variant="primary") |
| |
| with gr.Column(): |
| code_output = gr.Code(label="Generated Agent Code", language="python") |
| |
| generate_btn.click( |
| generate_agent_code, |
| inputs=[agent_type, use_case, model_choice, include_memory, include_tools], |
| outputs=code_output |
| ) |
| |
| |
| with gr.TabItem("🤖 Try an Agent"): |
| gr.Markdown(""" |
| ### Interactive Agent Demo |
| |
| Experience what AI agents can do. This is a simulation - in the course, |
| you'll build real agents that connect to actual AI models. |
| """) |
| |
| with gr.Row(): |
| with gr.Column(): |
| demo_agent_type = gr.Radio( |
| label="Select Agent Type", |
| choices=["customer_service", "data_analyst", "content_creator"], |
| value="customer_service" |
| ) |
| user_input = gr.Textbox( |
| label="Your Message", |
| placeholder="Type your message to the agent...", |
| lines=3 |
| ) |
| send_btn = gr.Button("Send Message", variant="primary") |
| |
| with gr.Column(): |
| agent_response = gr.Markdown(label="Agent Response") |
| |
| send_btn.click( |
| simulate_agent_conversation, |
| inputs=[demo_agent_type, user_input], |
| outputs=agent_response |
| ) |
| |
| |
| with gr.TabItem("📖 Resources"): |
| gr.Markdown(""" |
| ### 🎯 Free Resources to Get Started |
| |
| #### 📺 Video Tutorials |
| - [Introduction to AI Agents](https://youtube.com/agenticai) (30 min) |
| - [Your First Prompt Engineering](https://youtube.com/agenticai) (45 min) |
| - [Building with No-Code Tools](https://youtube.com/agenticai) (60 min) |
| |
| #### 📄 Documentation |
| - [AI Agent Fundamentals Guide](https://docs.agenticai.academy) |
| - [Prompt Engineering Best Practices](https://docs.agenticai.academy/prompts) |
| - [API Integration Handbook](https://docs.agenticai.academy/apis) |
| |
| #### 💬 Community |
| - [Discord Server](https://discord.gg/agenticai) - 5,000+ members |
| - [GitHub Repository](https://github.com/agenticai-academy) |
| - [LinkedIn Group](https://linkedin.com/groups/agenticai) |
| |
| #### 🏆 Success Stories |
| - **Sarah M.**: Marketing Manager → AI Consultant ($150K → $225K) |
| - **James L.**: Developer → AI Agency Owner ($30K/month revenue) |
| - **Tech Corp**: Trained 50 developers, saved $2M through automation |
| |
| #### 🎓 Certifications |
| 1. **Certified AI Agent Practitioner** - Entry level certification |
| 2. **Certified AI Agent Developer** - Professional certification |
| 3. **Certified Enterprise AI Architect** - Advanced certification |
| |
| #### 💰 Pricing |
| - **Starter**: $35/month - Core curriculum access |
| - **Professional**: $60/month - Full features + certification |
| - **Enterprise**: Custom pricing - Team features + support |
| |
| ### 📞 Contact |
| - Email: support@agenticai.academy |
| - Schedule Demo: [Book a Call](https://calendly.com/agenticai) |
| """) |
|
|
| |
| if __name__ == "__main__": |
| app.launch() |
