An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
Welcome to Microsoft Q&A
Hello @John Lamelas I hope you are doing well,
Thank you for sharing the example. Based on the text you've provided, I don't see anything that would obviously violate Microsoft Copilot's safety policies. The content appears to be a historical/genealogical narrative describing family lineage and immigration history.
I did notice that you referenced Microsoft 365 Message Center incident MC1172532. If your image-generation failures began around October 13 and coincide with the timeframe of that incident, there may be a service-side issue rather than a problem with the genealogy content itself.
A few questions that may help narrow this down:
- Are the failures occurring when generating new images from text, editing existing images, or both?
- Does the Responsible AI rejection occur with every genealogy-related prompt, or only with specific families, locations, or historical content?
- If you start a completely new Copilot chat and submit a simplified prompt based on the same text, does it still fail?
If issue started at a specific point in time and the content appears benign, I recommend submitting feedback directly from the affected Copilot session using the thumbs down option and including:
- The exact prompt
- The date the issue began (October 13)
- The Copilot application being used
- A note that the prompt is genealogical/family-history content
If you're using a work or school account, your Microsoft 365 administrator should also review the current status of MC1172532 in the Microsoft 365 Message Center.
References
- Microsoft 365 Message Center: https://admin.microsoft.com
- Microsoft Copilot image generation: https://support.microsoft.com/copilot/using-image-generation-in-microsoft-copilot
- Copilot feedback process: https://support.microsoft.com/privacy/microsoft-copilot/providing-feedback
If my answer helped you resolve your issue, please consider marking it as the correct answer. This helps others in the community find similar solutions. Thanks!