As organizations adopt AI agents, trust becomes one of the most important design requirements. This is especially true in regulated environments, where security, governance, auditability, and data protection cannot be added as an afterthought.

This session explores how to build trusted service agents using Microsoft Foundry and security controls such as Microsoft Defender for AI. We will look at how to embed governance into agentic workflows, enforce model and agent-level guardrails, apply policy-first controls such as PII redaction, and include continuous evaluation and monitoring across the workflow.

The session demonstrates how developer teams, SecOps teams, and AI platform teams can work together to design AI agents that are not only powerful, but also secure, compliant, and ready for enterprise use.

Session : Microsoft Tech Connect , Seattle. Feb 08'26
Level: Intermediate / Advanced
Format: Breakout
Duration: 45 minutes