tech
New Microsoft tool lets devs spin up AI behavior tests using text descriptions
Microsoft on Tuesday took the wraps off Adaptive Spec-driven Scoring for Evaluation and Regression Testing, an open source framework for spinning up AI evaluations.
TL;DR
- Microsoft launched ASSERT (Adaptive Spec-driven Scoring for Evaluation and Regression Testing), an open-source framework.
- ASSERT simplifies AI behavior testing for specific products and services.
- The framework turns natural-language descriptions of goals and policies into scored tests.
- It generates problem scenarios and test cases, runs them, and scores the results, recording AI system paths.
- Developers can customize evaluations with system context, tools, and constraints.
- ASSERT can be used during development, after deployment, and for continuous monitoring.
- This release aligns with a broader industry shift towards repeatable testing and regression checks in AI.