Meta details how Catching JiTTests generates bug-finding tests before code lands
AIMeta says its Catching Just-in-Time Tests (JiTTests) have moved from research prototype into production, where they generate executable tests that fail on code changes before they land. The system uses two generation workflows and filters weak catches with an LLM-as-Judge ensemble and a rule-based assessor, then has engineers review results at an aggregate level.
AIWhy it matters.
The post explains how the method is built and reports deployment results, which help readers judge whether AI-generated tests can work at large codebase scale.
Source details
Engineering at Meta · engineering.fb.comPublished · added here
Original title: Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale