All sessions
Track MSponsor Session
Evaluating and optimizing AI agents: from observability to continuous improvement
Chang Liu
- When
- Thursday, July 21:30 PM – 1:50 PM · 20 min
- Where
- Track MSan Francisco, CA · imported from ai.engineer's public schedule feed
About this session
AI agents don’t behave like traditional systems. Learn how to evaluate outputs, trace behavior, and apply a continuous loop to improve performance across prompts, tools, and models. Using signals grounded in real-world context via Foundry IQ, see how evaluation, tracing, and optimization come together to turn production usage into measurable improvements over time.
Speaker
Chang Liu
Senior Product Manager, Microsoft
Chang Liu is a Senior Product Manager at Microsoft working on Azure AI Foundry evaluation and agent quality tooling, including metrics for quality and safety in agentic applications.
More in Track M
- Get Started with Models in Microsoft Foundry to Build AI AppsMonday, June 29 · 9:00 AM – 10:15 AM · Track M
- From zero to deployed on Azure with AI agentsMonday, June 29 · 11:05 AM – 12:05 PM · Track M
- Observe, optimize and protect your hosted agents in Microsoft FoundryMonday, June 29 · 2:20 PM – 3:35 PM · Track M
- Build agents fast with GitHub Copilot (from idea to working app)Tuesday, June 30 · 10:45 AM – 11:05 AM · Track M
- Use Copilot across CLI, dev, and cloud workflows to move faster end-to-endTuesday, June 30 · 11:40 AM – 12:00 PM · Track M
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.