Explore the Council Chatbot
Go beyond the basics - experiment, understand the architecture, and test the limits
Great! You've deployed the demo
Now let's walk through what you just deployed and see it in action.
Start WalkthroughChoose your next step
Generate Evidence Pack
Create your business case documentation with what you've learned.
Generate Evidence PackExplore the Council Chatbot
Go beyond the basics - experiment, understand the architecture, and test the limits
Exploration progress
Complete 3 or more activities for essential exploration
Choose your exploration path
Explore through screenshots, diagrams, and guided interactions. No coding required.
Time: 25 minutes
Explore through AWS Console, architecture diagrams, and code inspection.
Time: 35 minutes
What Can I Change? 5 guided experiments
Test the chatbot's capabilities with these safe experiments. Each one teaches you something about how AI-powered chatbots work.
Ask Outside the Knowledge Base
What you'll learn: The chatbot has boundaries - it only answers from its training data
Try this:
What's the weather going to be tomorrow?
Multi-Turn Conversation
What you'll learn: Context retention reduces repetitive questions from residents
Try this:
First: "When are bins collected?"
Then: "What about recycling?"
Semantic Understanding
What you'll learn: AI understands intent, not just keywords
Complex Multi-Part Question
What you'll learn: Complex questions may need to be broken down
Try this:
I need to report a pothole on my street, check when my bins are collected, and find out about...
Welsh Language Input
What you'll learn: Welsh language support for councils in Wales
Try this:
Pryd mae'r biniau'n cael eu casglu?
How Does It Work? Architecture tour
Understand the technology behind the chatbot. Choose your path:
Tour options
Visual Architecture Tour
Follow the journey of a question from resident to response.
-
Resident Asks Question
A resident types a question in the web interface
-
Question Reaches Lambda
AWS Lambda function receives and processes the request
-
Bedrock Understands Intent
AWS Bedrock AI model interprets what the resident wants
-
Knowledge Base Searched
Council documents and FAQs are searched for the answer
-
Response Generated
AI generates a helpful, accurate response
Console Architecture Tour
Navigate the AWS Console to see the real infrastructure.
-
Lambda Function
Function code, environment variables, CloudWatch logs
Open in AWS Console (opens in new tab)
-
Bedrock Model
Model selection, inference parameters, token limits
Open in AWS Console (opens in new tab)
-
DynamoDB Conversation History
Table schema, session data, TTL settings
Open in AWS Console (opens in new tab)
-
CloudWatch Logs
Request/response logs, latency metrics, errors
Open in AWS Console (opens in new tab)
-
API Gateway
Endpoint configuration, CORS settings, throttling
Open in AWS Console (opens in new tab)
Test the Limits 3 boundary challenges
Every system has limits. Understanding them helps you plan for real-world usage.
Token Overload
Safe to try This experiment won't break anything. You can always reset.Challenge: Paste a 5000+ character text to see how the chatbot handles it
Expected behavior: Chatbot may truncate input or ask for a shorter question
Business implication: Complex documents may need summarization before chatbot processing
How to recover
Sensitive Topic Handling
Safe to try This experiment won't break anything. You can always reset.Challenge: Ask about a potentially sensitive topic
Expected behavior: Chatbot provides appropriate guidance without speculation
Business implication: Guardrails protect both residents and the council
How to recover
Rate Limiting
Safe to try This experiment won't break anything. You can always reset.Challenge: Send 10 rapid-fire questions in quick succession
Expected behavior: May see brief delays or throttling after many requests
Business implication: Rate limits protect the system and control costs