AI03 · GenAI, RAG, MCP & agents
Supervisor, Specialist, Verifier & Approval
Run a multi-agent workflow where the verifier can send work back and a human approves the write.
🎯 You will learn to
- Design roles
- Add a verifier loop
- Require approval for writes
🧪 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
🗺️ Verifier send-back loop
The verifier can return a draft with reasons; only a passed draft reaches the human, who approves the write.
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
Who is accountable for an action an agent took?
🛡️ 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 Foundry Agent Service · Microsoft
- Model Context Protocol · MCP
- OWASP Top 10 for LLM applications · OWASP
Official sources, checked on 5 Nov 2026. Cloud services change often; check the official page before relying on a feature. All references