Ai Agent Real Time Protection
In brief
The page now states that the device-level setting enables or disables prompt evidence collection when AI agent runtime protection is configured, with a link to configuration guidance.
What Defender admins need to know
Administrators can use the linked guidance to understand and configure prompt evidence collection for local Windows agents.
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.
By default, Microsoft Defender includes prompt snippets exchanged between the user and the agent as evidence in each alert.
Note
For local Windows agents, the device-level setting enables or disables the collection of prompt evidence when AI agent runtime protection is configured. See Configure prompt evidence collection.
To configure this setting, go to Settings > Security for AI > Prompt evidence collection, then toggle Enabled on or off.
When enabled, the snippets include only the portions of user prompts or agent responses identified as suspicious and relevant to security classification. Sensitive data and secrets are redacted; however, customer conversations might still be sensitive in nature. The evidence is available in the Defender portal as part of each alert.
@@ -9,8 +9,8 @@ feedback_product_url: https://techcommunity.microsoft.com/t5/microsoft-365-defen uhfHeaderId: MSDocsHeader-MicrosoftDefender manager: orspodek description: Learn how to block unsafe AI agent actions in real time and configure real-time protection rules in Microsoft Defender.-ms.author: guywild-author: guywi-ms+ms.author: joshbregman+author: j0shbregman ms.reviewer: itaicohen ms.service: microsoft-defender ms.update-cycle: 180-days@@ -142,6 +142,10 @@ On the **Real-time protection** page, select a rule to open its details pane, wh
By default, Microsoft Defender includes prompt snippets exchanged between the user and the agent as evidence in each alert.
+Note
+
+For local Windows agents, the device-level setting enables or disables the collection of prompt evidence when AI agent runtime protection is configured. See [Configure prompt evidence collection](/en-us/defender-endpoint/configure-ai-agent-runtime-protection#configure-prompt-evidence-collection).
+
To configure this setting, go to **Settings** > **Security for AI** > **Prompt evidence collection**, then toggle **Enabled** on or off.
When enabled, the snippets include only the portions of user prompts or agent responses identified as suspicious and relevant to security classification. Sensitive data and secrets are redacted; however, customer conversations might still be sensitive in nature. The evidence is available in the Defender portal as part of each alert.
