The content was filtered due to Responsible AI restrictions. Error Code: ContentFiltered Conversation Id

Question

The content was filtered due to Responsible AI restrictions. Error Code: ContentFiltered Conversation Id

john john Pter 1,245

I define the knowledge source as this simple docx document, with this content:-

image-20251025195318-1

and i change the Moderation to low:-

image-20251025195352-3

then i added a trigger when email is arrived, but this will raise the following error:-

"The content was filtered due to Responsible AI restrictions. Error Code: ContentFiltered Conversation Id":-

User's image

any advice?

Karan Shewale 2,020 Reputation points Microsoft External Staff

2025-10-27T05:36:42.9066667+00:00

Thanks for bringing this issue to our attention. We will check and update you soon.

1 answer

Your answer

Karan Shewale 2,020 Reputation points Microsoft External Staff

2025-10-27T05:36:42.9066667+00:00

Thanks for bringing this issue to our attention. We will check and update you soon.

Answer 1

Hi John, this error occurs because Microsoft’s Responsible AI system detected content that might violate safety or compliance rules. Even when moderation is set to Low, baseline filters still apply to prevent unsafe or risky outputs. The issue often happens when your knowledge source includes links, commands, or phrases that sound like instructions, such as “Encourage all users” or “Pin your hub sites.” It can also occur when using Generative AI orchestration with email triggers, as this combination is considered high-risk because it may send unmoderated content externally. Responsible AI filters block anything that could be interpreted as unsafe, sensitive, or potentially harmful.

To reduce or fix this issue, start by cleaning up your knowledge source. Remove imperative phrases like “Encourage all users” or “Pin your hub sites,” avoid embedded links or replace them with plain text, and keep the tone neutral and descriptive rather than instructional. If possible, disable Generative AI orchestration for email triggers and use static responses or classic QnA for flows that send emails. Always add a fallback response, such as: “Sorry, I can’t process this request right now.” You can also check logs in Azure Application Insights to identify which part of the content triggered the filter. If orchestration is essential, wrap prompts with clear instructions like: “Summarize this text in a neutral tone without commands or links.”

Official References

Thank you.

Karan Shewale.

If this response resolves your issue, please Accept the answer and, if helpful, click the “Upvote” button. Your feedback helps us improve and assist others more effectively.

john john Pter 1,245 Reputation points

2025-10-28T20:38:07.51+00:00

@Karan Shewale i removed the text you mentioned and urn off orchestration, still the i am getting this message:-

"Error Message: The content was filtered due to Responsible AI restrictions."
Karan Shewale 2,020 Reputation points Microsoft External Staff

2025-10-29T10:26:06.19+00:00

Hi John,

Thanks for validating. Even with the text removed and orchestration disabled, baseline Responsible AI filters still apply for email-based actions. Email triggers are treated as high-risk surfaces, so the platform enforces stricter safety controls that cannot be bypassed through moderation settings. This indicates the remaining KB content or generated output is still being classified as non-compliant at source.

I recommend testing with a minimal neutral KB (one factual sentence, no URLs, no advisory verbs) to isolate the trigger. If the filter still fires, it confirms the constraint is at the email action layer rather than the content itself.

Share via

The content was filtered due to Responsible AI restrictions. Error Code: ContentFiltered Conversation Id

1 answer

Your answer