Category
stayInformed
Severity
normal
Major change
False
Last modified
2026-07-07 22:11:13
Summary source
Azure OpenAI (gpt-4.1)
Action by (Graph)
—
Action by (AI)
2026-07-15 00:00:00
Services
Power Platform
Tags
New feature
Master tags
Admin, Compliance
Roadmap IDs
One-line summary
Admins can use configurable safety graders to evaluate AI responses for policy violations in Power Platform governance, with public preview starting July 15, 2026.
Similar updates
More like thisMC1197917 Power Platform admin center – Review security role descriptions and definitions
MC1193456 Power Platform – Power Platform Monitor Overview page and predefined alerts
MC1194567 Power Platform Monitor - Announcing Copilot Studio agent health metrics and alerts in Public Preview
MC1190074 Power Pages - Enhance governance for non-production site visibility
MC1190207 Manage Non-Microsoft Generative AI Usage Across Your Organization
MC1193689 Microsoft baseline security mode for Office, SharePoint, Exchange, Teams, and Entra
Details
Body (from Message Center)
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 July 15, 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.
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.
Raw JSON (for debugging)
Expand/collapse the full payload below.
Show/hide raw
{
"snapshot_item": {
"action_required_by": null,
"ai_action_required_by": "2026-07-15T00:00:00Z",
"ai_actions": [],
"ai_master_tags": [
"Admin",
"Compliance"
],
"ai_model": "gpt-4.1",
"ai_summary": "Admins can use configurable safety graders to evaluate AI responses for policy violations in Power Platform governance, with public preview starting July 15, 2026.",
"ai_topics": [
"Power Platform"
],
"category": "stayInformed",
"details_map": {},
"id": "MC1419786",
"importance": 4,
"is_major_change": false,
"last_modified": "2026-07-07T22:11:13Z",
"ms_products": [
"Power Platform"
],
"platforms": null,
"roadmap_ids": [],
"services": [
"Power Platform"
],
"severity": "normal",
"tags": [
"New feature"
],
"title": "Microsoft Power Platform governance and administration - Safety Grader"
}
}