Managing AI Agents with Microsoft Agent 365

Microsoft Agent 365 is the control plane for agents - it extends the infrastructure you use to manage people (identity, access, data protection, threat defense) to AI agents, regardless of where they originate (Microsoft, Copilot Studio, partner/third-party including agents built on Anthropic Claude, OpenAI, or Google Gemini, or custom-built). It organises the work into three pillars: observe, govern, and secure. Generally available for Commercial since 1 May 2026, licensed per user, with Microsoft E5 as the recommended prerequisite.

When to use

Standing up enterprise-wide management for a growing fleet of AI agents - when you need a single inventory, consistent lifecycle and access controls, and unified security across agents built on different platforms. Use it as the orchestration layer that ties together Entra, Purview, and Defender for agents.

Do not use this skill for Purview data-security controls on a single agent in isolation (use purview-agent-365-security), or to remediate Microsoft 365 Copilot oversharing of end-user content (use purview-copilot-oversharing / m365-oversharing).