Microsoft Ignite LAB663: a hands-on loop for improving agents with Copilot traces and Model Router
lee_stott · x · 2026-11-18
Microsoft's LAB663 at MS Ignite walks through a continuous agent-improvement loop: get your agent working and gather traces with GitHub Copilot, define what "good" means (messages, getlogs, world state), improve the agent system with cost-effectiveness review, then swap the fixed model for Model Router to raise quality and control cost.
Lab docs, an agent optimization workshop, Model Router docs, and Agent Optimizer docs are provided, encouraging attendees to run a controlled comparison against their own baseline after the event.
More from coding & agent
- AI prompt kit claims a faceless GTA 6 clipping page can make up to $10k/month — CurieuxExplorer · 2026-11-18
- Stitch launches AI agents natively in its banking OS, under bank permissions — CurieuxExplorer · 2026-11-18
- Codex 0.95 adds customizable keyboard shortcuts — charlieholtz · 2026-11-18
- Seroter's Daily Reading: Levels of Agentic Engineering and Git's Future in the AI Era — rseroter · 2026-11-18
- "The model has no idea what its own biases are": designers on AI slop — petergyang · 2026-11-18
- Agent tweak is 15% faster at nearly same cost — the model admitted it overweighted raw token counts — dosco · 2026-11-18