Microsoft Defender for Endpoint
Endpoint protection

Configure Ai Agent Runtime Protection

In brief

The documentation now specifies that both settings use 0 for Disabled, 1 for Block, and 2 for Audit.

What Defender admins need to know

Administrators can use these values when configuring or interpreting the settings.

Summaries are generated from the documentation change itself.

Documentation change

The comparison below shows only the changed extract. Use the full-page view for complete context.

  • To deploy the settings from the Microsoft Defender portal, your account has permission to manage endpoint security policies. For more information, see Prerequisites for managing endpoint security policies.
  • To review alerts, your account has a supported Microsoft Entra role, such as Security Reader, Security Operator, or Security Administrator, or a Microsoft Defender custom role with permission to read security data. For more information, see Required permissions to investigate alerts.

Note

During public preview, configure test devices to receive Microsoft Defender platform and engine updates from the Beta Channel. For configuration and verification instructions, see Create a custom gradual rollout process for Microsoft Defender updates.

Recommended deployment approach

Microsoft recommends the following phased rollout: powershell Get-MpPreference | Select-Object AiAgentProtection, AiAgentNetworkInspection 6.

For both settings, the numerical values are `0` (`Disabled`), `1` (`Block`), and `2` (`Audit`).
  1. Close the PowerShell window and any terminal windows used to run agents. Then open a new terminal window before starting the agent.

Tip