ContentFiltered Error on deployed AI agent built using Copilot studio

Question

I have been building a teams deployed AI agent for internal documentation with Copilot studio. I have a recurrent problem. It's throwing this error. "An error has occurred. Error code: ContentFiltered Conversation Id: a:1Ub--U2KmWiPxM9uhXTHTV2BM_83sLgcWOcPUZT8weL_4y_Tw0iEgef_TwK73eum09NWAqwCRVb94hqJLYHBvlK4SJca5eOJrHYFeyxxC_9Wo1pfac4SABsFT9B3OeZU1 Time (UTC): 2026-01-17T19:42:18.000Z

Answer 1

The error message you are encountering, "ContentFiltered", indicates that the AI agent has triggered a Responsible AI content moderation policy. This happens when the content generated or requested by the agent violates the guidelines set to prevent exposure to harmful or offensive material.

To troubleshoot this issue, you can follow these steps:

1. Check for Exceptions: Use Azure Application Insights to review telemetry from your agent events, including any triggered exceptions related to Responsible AI. You can run KQL queries to validate if your agent encountered any RAI exceptions.
2. Review Conversation Transcripts: Analyze conversation transcripts to identify the specific message that triggered the Responsible AI filter response. This can help you understand what content is being flagged and why.
3. Modify Input: If you identify specific inputs that lead to the error, consider modifying them to comply with Responsible AI guidelines.

For more detailed steps on how to connect Application Insights and analyze errors, you can refer to the documentation provided by Microsoft.

---

References:

• Resolve responsible AI content filter errors
• Check error exceptions with Azure Application Insights

AI-generated content may be incorrect. Read our transparency notes for more information.