Meta Deploys JiTTests to Catch Risky Code Changes Before Merge
Meta has moved its Catching Just-in-Time Tests (JiTTests) system from a research prototype into production infrastructure. The LLM-based tool generates executable tests intended to fail when a code diff introduces an unintended behavior change. It runs overnight on spare internal capacity and is designed to target risky changes before they are merged.
The system reported 74 privacy SEVs caught at the diff stage during the first half of 2026, while privacy SEV occurrence fell 20% over the same period. Engineers contacted by the system reported a 60% true-positive rate. An earlier deployment was less effective: only eight of 41 candidate catches were confirmed, a 19.5% rate, although four could have caused serious production failures.
A research analysis of 22,126 generated tests found that intent-aware JiTTests produced weak catches in 6.4% of tests and on 7.9% of diffs. LLM judges and deterministic RubFake rules reduced the human review workload by 70%. JiTTests remains available only inside Meta; the company has released neither its code and models nor an API.
Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.