Observe and control agents across any framework with open source tools | BRK250

Sarah Bird, Sandeep Atluri, and Mehrnoosh Sameki present a Microsoft Build 2026 breakout on shipping AI agents safely at enterprise scale, with a focus on governance, reliability, and controls that work across Microsoft Agent Framework and open-source stacks.

Overview

As AI agents move into production, the session focuses on how developers can own safety, governance, and reliability end to end:

Key topics covered

Common failure modes for AI agents

The session frames four major ways agents can fail:

Defining risks and roles as configuration

Rubric-based judging and evaluation

Automated test set creation

Safety regression and system controls

Agent Control Specification (ACS)

Continuous evaluations and attacker simulation

Resources