CSE60 · GenAI, RAG, MCP & agents
Multi-Agent Mission
A supervisor plans, a researcher looks things up, a writer drafts and a verifier checks, with a human approval before any change.
🎯 You will learn to
- Split work between agents
- Verify outputs
- Gate actions with approval
🧪 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
🗺️ Supervisor and specialists
The supervisor splits the mission; researcher, writer and verifier work in turn, and a human approves before anything is written.
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
When is one agent better than many?
🛡️ 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
- Agentic AI Lens (Well-Architected) · AWS
- Microsoft AI decision framework · Microsoft
- Model Context Protocol · MCP
- OWASP Top 10 for LLM applications · OWASP
- 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