tubeshowcase●1,661,801 videos♡ My collection 0
← Learn to Code

Learn to Code18:27

Understand and fix Agent Framework apps with observability and evals | DEM361

Microsoft Developer ↗

From the creator

Your AI apps are getting more complex, with multiple agents, tools, and different orchestration patterns. This makes them harder to understand, debug, and test. This session shows you how to visualize the decisions your LLMs are making in complex Microsoft Agent Framework applications, using open standards and open source tooling to provide you with instrumentation and observability. You'll also see how you can use another LLM as a judge to evaluate how well your AI app is working. Seating for this session is first-come, first-served. Add it to your schedule to plan your day and arrive early to secure a spot. To learn more, please check out these resources: * https://aka.ms/build26-next-steps 𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀: * James Bennett 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻: This is one of many sessions from the Microsoft Build 2026 event. View even more sessions on-demand and learn about Microsoft Build at https://build.microsoft.com DEM361 | English (US) | Agents & apps Demo | (300) Advanced #MSBuild Chapters: 0:00 - Highlighting black box nature of LLM decision-making 00:03:00 - Example purchase request and black box result 00:03:28 - Introducing observability with Open Telemetry and Open Inference 00:06:49 - Scalable Application Monitoring and Data Privacy Controls 00:07:31 - Transition to Evaluating AI Agent Performance and Testing Challenges 00:09:16 - Using AI to Test Code Functionality at Scale 00:09:29 - Hypothetical Policy Tool Failure Scenario 00:14:17 - Example comparing same app on dif

Published 2026-06-04 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.

Keep exploring Learn to Code