Update config.py

config.py

@@ -25,8 +25,10 @@ You are a supportive and knowledgeable tutor, embedded in a Shiny application th
    - Refer specifically to the slider and numeric inputs in the sidebar (“Population SD,” “Sample Size (each),” “Number of Random Samples,” “Confidence Level (%)”) to guide hands-on experimentation.
 
 3. **Address the Guiding Questions**  
-   - **Question 1:** “If you run 100 simulated experiments, how many experiments (red dots) failed to contain the true population mean within their 95% CI?”  
+   - **Question 1:** “If you run 100 simulated experiments, how many experiments (red dots) failed to contain the true population mean within their 95% CI? What about 10 or 1,000?”  
    - **Question 2:** “Why is it sometimes not exactly 5 red dots (i.e., sample means with 95% CIs that don’t include the population mean) even though 95% of the intervals are supposed to capture the true mean?”
+   - **Question 3:** "How does changing standard deviation and sample size affect the output?"
+   - **Question 4:** "What is the relationship between a confidence interval and standard error?"
    - **YOU ARE NOT ALLOWED TO DIRECTLY ANSWER THE GUIDING QUESTIONS.** Instead suggest how the student can use the app simulation to infer the answer.
 
 4. **Encourage Critical Thinking**  
@@ -85,7 +87,9 @@ For your own context and knowledge, use the UI and server code for this tab to i
           hr(),
           h4(strong("Guiding Questions:")),
           h5("1. If you run 100 simulated experiments, how many experiments (red dots) failed to contain the true population mean within their 95% CI?"),
-          h5("2. Why is it sometimes not exactly 5 red dots (samples means with 95% CIs that don't include the population mean?)")
+          h5("2. Why is it sometimes not exactly 5 red dots (samples means with 95% CIs that don't include the population mean?)"),
+          h5("3. How does changing standard deviation and sample size affect the output?"),
+          h5("4. What is the relationship between a confidence interval and standard error?")
         ),
         mainPanel(
           plotOutput("plot_tab2"),
@@ -174,7 +178,7 @@ For your own context and knowledge, use the UI and server code for this tab to i
 ###########################################################################################
 # Model Configuration
 ###########################################################################################
-ai_model = "gpt-4o"         # Choose from: gpt-4o, gpt-4o-mini, etc.
+ai_model = "gpt-4.1"         # Choose from: gpt-4o,gpt-4.1, gpt-4o-mini, etc.
 temperature = 0.05           # 0 to 1: Higher values = more creative responses
 max_tokens = 500            # 1 to 2048: Max tokens in the response
 frequency_penalty = 0.5     # 0 to 1: Higher values = more penalty for repeating phrases
@@ -188,13 +192,13 @@ instructions = '''This is a basic chatbot template. Place user instructions here
 
 opening_message = '''👋 **Welcome to the Confidence Intervals Chatbot!**
 
-Hello! I’m Pliny, your AI tutor for exploring confidence intervals in this Shiny app. I’m here to guide you as you experiment with repeated sampling, confidence levels, and population variability. Feel free to ask me questions about:
-- Interpreting your multiple samples, their means, and their CIs.
-- How changing your population SD, sample size, or confidence level affects how often the true mean is included in your confidence intervals.
-- Real-world implications of repeated sampling when estimating unknown parameters.
-
-I encourage you to think critically as you generate multiple samples, observe how many confidence intervals fail to include the true mean, and compare results across different settings. Let’s work together to deepen your understanding of the underlying statistics, one group of samples at a time.
+I'm here to facillitate as you attempt to use this simulation to answer the following:
+   - **Question 1:** “If you run 100 simulated experiments, how many experiments (red dots) failed to contain the true population mean within their 95% CI? What about 10 or 1,000?”  
+   - **Question 2:** “Why is it sometimes not exactly 5 red dots (i.e., sample means with 95% CIs that don’t include the population mean) even though 95% of the intervals are supposed to capture the true mean?”
+   - **Question 3:** "How does changing standard deviation and sample size affect the output?"
+   - **Question 4:** "What is the relationship between a confidence interval and standard error?"
 
-Lastly, remember that **generative AI can make errors**. These chats do not replace verified classroom resources but can serve as a springboard for exploration and understanding. I look forward to discussing your discoveries with you!'''
+See what patterns you find when you adjust the simulation's parameters and repeatedly generate sample means.
+'''
 
 warning_message = "**Generative AI can make errors and does not replace verified and reputable online and classroom resources.**"