Meta Deploys JiTTesting LLM Bug-Catching System to Production
Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale
JiTTesting shifts test generation from pre-planned suites to on-demand tests written exactly when a risky diff appears, with humans confirming rather than authoring. Engineering teams running large monorepos can study Meta's human-on-the-loop design as a template for adding LLM-generated checks without letting unreviewed code gate merges. The paper gives concrete deployment lessons rather than a lab-only prototype.
Meta reports production results for its Just-in-Time Tests (JiTTests) approach, which uses large language models to generate tests that catch bugs as code changes land. The team describes a human-on-the-loop workflow where engineers review and confirm LLM-generated tests before they take effect. The details appear in the paper "Just-in-Time Catching Test Generation at Meta," published on 29 Oct 2026 on Meta's engineering blog. The company says the system has shown positive impact over the past year of production deployment.
Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale
Over the last year we’ve been sharing our work leveraging large language models to catch bugs on the fly — a novel approach we call Catching Just-in-Time Tests (JiTTests). Now, we’re sharing the results and positive impact we’ve seen with Catching JiTTests deployed into production. Our paper, “Just-in-Time Catching Test Generation at Meta,” fully details [...] Read More... The post Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale appeared first on Engineering at Meta .
