Modern agents fail in ways traditional monitoring can’t catch. In this hands-on lab, learn how Microsoft Foundry Observability helps you move from prototype → production with context-specific evaluation suites (auto-generated evaluators + test datasets) wired into developer workflows via skills/MCP tooling for hosted agents. Then scale quality with continuous evaluation, trace-linked analysis, and adaptive red teaming—and walk away with a sandbox to explore additional features on your own.
Track M sessions at AI Engineer World's Fair 2026 in San Francisco.
Monday, June 29, 2026
2:20 PM - 3:35 PM·1h 15m
Track M · Room 2001
Capacity: 250 attendees
Sign in to add this talk to your schedule.

Pamela Fox
Principal Cloud Advocate
Microsoft
@pamelafox
Principal Cloud Advocate at Microsoft focused on Python and Azure; previously worked in developer advocacy/engineering roles at Google, Coursera, and Khan Academy, and taught computer science at UC Berkeley.