A Guth Labs publication ↗
Back to News

Zenity expands Microsoft agent monitoring and Sentinel security alerts

A transparent green glass shield containing interconnected nodes and gold light.

Zenity expanded its Microsoft agent-security coverage on November 17, adding monitoring across coding, office and employee-built assistants and upgrading its Microsoft Sentinel integration. The company announcement describes different levels of protection for different products, rather than uniform prevention everywhere.

Zenity says its Sentinel integration now streams contextual alerts instead of raw logs. Eligible findings for supported Copilot Studio and Microsoft Foundry agents can contribute to Microsoft’s dynamic agent-risk assessment. Broader visibility of that assessment in Agent 365, Defender, Entra and Purview depends on supported capabilities becoming available.

For Claude Enterprise in Microsoft 365 and the GitHub Copilot coding agent in GitHub Enterprise, Zenity reports telemetry, findings and inline prevention. It says Entra ID can resolve coding-agent users when enterprise settings obscure actor names.

Other integrations have narrower scope: Copilot Studio receives telemetry and limited inline prevention, while Agent Builder and Copilot Cowork receive telemetry and findings. Zenity also says its integration has migrated to the new Microsoft Foundry Agent Service.

The significance is consolidation: agent activity can enter the same security queue as other incidents. Buyers still need to check each integration’s prevention capabilities rather than treating ecosystem-wide coverage as a guarantee that every action can be blocked.

Sources and citations

Revision history

Published .