MC1419786 High
Microsoft Power Platform governance and administration - Safety Grader
Summary AI-generated
Admins can configure safety graders to assess AI responses in Power Platform for policy violations, with public preview starting August 31, 2026.
Written by Azure OpenAI (gpt-4.1) from the text of the post below. It can be incomplete or wrong; the original post is authoritative.
Similar posts
Search for more like this- MC1434634 Microsoft Power Platform governance and administration - Evaluation for AI Node
- MC1472451 Power Platform - Multi-Grader Comparison
- MC1443077 Power Platform - Overall Score
- MC1471895 Power Platform admin center - Ask advisor
- MC1486027 Microsoft Power Platform governance and administration - Secure Dataverse record with column-based filtering
- MC1387846 Dynamics 365 Customer Service - Enforce governance policy
Original post from Microsoft
Update: Release of this feature has been updated.
We are announcing the ability to evaluate AI responses using configurable safety graders to identify unsafe or policy-violating outputs in Microsoft Power Platform governance and administration. This feature will reach public preview on August 31, 2026.
How does this affect me?
Admins will be able to configure specific safety criteria to evaluate AI responses prior to them being sent to identify policy-violating outputs. Once configured, the Safety Grader will be able to do the following:
This message is for awareness, and no action is required.
We are announcing the ability to evaluate AI responses using configurable safety graders to identify unsafe or policy-violating outputs in Microsoft Power Platform governance and administration. This feature will reach public preview on August 31, 2026.
How does this affect me?
Admins will be able to configure specific safety criteria to evaluate AI responses prior to them being sent to identify policy-violating outputs. Once configured, the Safety Grader will be able to do the following:
- Evaluate responses against safety criteria.
- Detect unsafe or undesirable outputs.
- Combine safety evaluations with other graders.
- Provide detailed explanations and evidence supporting the evaluation for each result.
This message is for awareness, and no action is required.