AI01 · GenAI, RAG, MCP & agents
RAG Chunking, Hybrid Retrieval & Citations
Compare retrieval settings on a test set of questions and measure how often the right chunk comes first.
🎯 You will learn to
- Measure retrieval quality
- Tune chunking
- Use hybrid ranking
🧪 Live environment
Runs entirely in your browser: nothing is installed, no real cloud account is used and your code is never sent to our server.
Loading the lab…
✅ Steps & checkpoints
🗺️ Hybrid retrieval evaluation
Keyword and vector results are fused; a labelled test set measures how often the right chunk ranks first.
The 2D diagram shows the exact flow, ports and trust boundaries. The 3D scene is a concept view of the same parts; packets travel along the same arrows.
🤔 Think about it
Why measure retrieval separately from the final answer?
🛡️ Safety & cost
The agents are deterministic simulations: no model is called and no real tool is executed. Write tools always need human approval.
🧹 Cleanup
Nothing to clean up.
📚 Reference documents
- Retrieval-augmented generation in Azure AI Search · Microsoft Learn
- Azure AI Search · Microsoft Learn
- Bedrock knowledge bases · AWS
- Model Context Protocol · MCP
- OWASP Top 10 for LLM applications · OWASP
- Agentic AI Lens (Well-Architected) · AWS
- Microsoft Foundry Agent Service · Microsoft
Official sources, checked on 5 Nov 2026. Cloud services change often; check the official page before relying on a feature. All references