Exploration progress

0 of 10 activities completed

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

5 min Safe to try Experiment

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?

Start activity Ask Outside the Knowledge Base - 5 min

Multi-Turn Conversation

5 min Safe to try Experiment

What you'll learn: Context retention reduces repetitive questions from residents

Try this: First: "When are bins collected?" Then: "What about recycling?"

Start activity Multi-Turn Conversation - 5 min

Semantic Understanding

5 min Safe to try Experiment

What you'll learn: AI understands intent, not just keywords

Start activity Semantic Understanding - 5 min

Complex Multi-Part Question

5 min Safe to try Experiment

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...

Start activity Complex Multi-Part Question - 5 min

Welsh Language Input

5 min Safe to try Experiment

What you'll learn: Welsh language support for councils in Wales

Try this: Pryd mae'r biniau'n cael eu casglu?

Start activity Welsh Language Input - 5 min

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.

  1. Resident Asks Question

    A resident types a question in the web interface

    Resident Asks Question
  2. Question Reaches Lambda

    AWS Lambda function receives and processes the request

    Question Reaches Lambda
  3. Bedrock Understands Intent

    AWS Bedrock AI model interprets what the resident wants

    Bedrock Understands Intent
  4. Knowledge Base Searched

    Council documents and FAQs are searched for the answer

    Knowledge Base Searched
  5. Response Generated

    AI generates a helpful, accurate response

    Response Generated

Console Architecture Tour

Navigate the AWS Console to see the real infrastructure.

  1. Lambda Function

    Function code, environment variables, CloudWatch logs

    Open in AWS Console (opens in new tab)

    AWS Console showing Lambda Function
  2. Bedrock Model

    Model selection, inference parameters, token limits

    Open in AWS Console (opens in new tab)

    AWS Console showing Bedrock Model
  3. DynamoDB Conversation History

    Table schema, session data, TTL settings

    Open in AWS Console (opens in new tab)

    AWS Console showing DynamoDB Conversation History
  4. CloudWatch Logs

    Request/response logs, latency metrics, errors

    Open in AWS Console (opens in new tab)

    AWS Console showing CloudWatch Logs
  5. API Gateway

    Endpoint configuration, CORS settings, throttling

    Open in AWS Console (opens in new tab)

    AWS Console showing API Gateway

Test the Limits 3 boundary challenges

Every system has limits. Understanding them helps you plan for real-world usage.

Safe to explore: These challenges won't break anything. The system is designed to handle edge cases gracefully.
1

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
Ask a shorter, focused question
2

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
Chatbot redirects to appropriate channels
3

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

How to recover
Wait a few seconds between questions

What's Next?

Take It Further

Ready for production? See cost projections, security guidance, and customization options.

View production guidance

Generate Evidence Pack

Create a committee-ready PDF documenting what you learned and experienced.

Create Evidence Pack