Post Content
As AI agents move into production, developers own safety, governance, and reliability across Microsoft Agent Framework and open-source stacks. This session shows how to govern agents end to end: turning your requirements into context-aware evaluations, stress-testing against adversarial risks, applying open controls that work across frameworks, and keeping humans in the loop on high-stakes actions. Leave with a blueprint for shipping agents at enterprise scale.
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
* https://aka.ms/build/foundrydiscord
𝗦𝗽𝗲𝗮𝗸𝗲𝗿𝘀:
* Sarah Bird
* Sandeep Atluri
* Mehrnoosh Sameki
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
BRK250 | English (US) | Responsible AI
Breakout | (300) Advanced
#MSBuild
Chapters:
0:00 – Four major ways AI agents can fail: instruction, information integrity, tool misuse, and emergent behavior
00:13:45 – Defining agent risks and roles in YAML format
00:14:15 – Introduction of rubric-based judge and evaluation process
00:16:29 – Automated creation of test sets: Singleton vs multi-turn scenarios
00:22:44 – Discussion on AI safety regression and system controls
00:25:00 – Introduction of Agent Control Specification (ACS) to unify control logic
00:25:59 – Explanation of ACS operation between runtime and policy engine
00:36:33 – Introduction to Continuous Evaluations and Reinforcement Learning-based Attackers
00:44:50 – Call for Community Collaboration to Build Trustworthy AI Read More Microsoft Developer
