RM560707 - Microsoft Purview: Information Protection – Auto-labeling Simulation Evaluation

Microsoft 365 Roadmap

Summary

The Simulation Grader helps admins understand and improve auto‑labeling accuracy before enforcing a policy. When enabled during simulation, matched items are evaluated by an AI-powered grader to determine whether each match is a true positive or false positive, along with an explanation of why the content matched. The results roll up into clear policy‑level accuracy insights and file‑level evaluation details, giving admins confidence to refine conditions, upgrade to smarter classifiers, and move policies to enforcement with greater trust.

Published

May 20, 2026

Status

In development

Release

General Availability
Preview

Platforms

Web

Service

Microsoft Purview

Tag

In development
General Availability
Preview
Worldwide (Standard Multi-Tenant)

Cloud

Worldwide (Standard Multi-Tenant)

Description

The Simulation Grader helps admins understand and improve auto‑labeling accuracy before enforcing a policy. When enabled during simulation, matched items are evaluated by an AI-powered grader to determine whether each match is a true positive or false positive, along with an explanation of why the content matched. The results roll up into clear policy‑level accuracy insights and file‑level evaluation details, giving admins confidence to refine conditions, upgrade to smarter classifiers, and move policies to enforcement with greater trust.

GA date: June CY2026

Preview date: May CY2026