Changelog

[1.0.1] - 2025-11-03

Updated the Agent Output.

[1.0.0] - 2025-09-30

Initial Release

First release of Classification Optimizer! This version provides comprehensive analysis of your Purview classification effectiveness with data-driven recommendations for improvement.

What's included:

  • SIT baseline metrics showing detection frequency and distribution

  • Co-occurrence pattern analysis with statistical metrics (support, lift, conditional probability)

  • New composite SIT recommendations based on real-world detection patterns

  • Parameter tuning suggestions to reduce false positives and improve accuracy

  • Trainable classifier candidates for complex, context-dependent patterns

  • Policy optimization recommendations (scoping, grouping, rule tuning)

  • Configurable analysis modes (quick, standard, deep) to balance speed vs detail

  • Debug mode with detailed execution logs and skill outputs

  • Integration with Security Copilot for natural language queries

Last updated

Was this helpful?