New Microsoft tool lets devs spin up AI behavior tests using text descriptions | TechCrunch
Summary
Microsoft released ASSERT, an open source framework for testing how AI systems behave in application-specific contexts. The tool turns natural-language policies and goals into structured tests, generates scenarios, runs them against a target system, and scores the results. It also records the AI system’s paths and tool calls so developers can inspect failures more easily. The launch addresses a gap in broader model evaluations by focusing on product- and policy-specific behavior, both during development and after deployment.
Classifications
industries
No industries detected
applications
Accounting and Taxes
AskAI Classifications
Labels
SaaS
Cloud Computing
Enterprise Software
Linked Companies
METR
n/a