Agents & Products

Meet Meta’s JiTTests: LLM-Generated Tests Designed to Fail Before Risky Code Lands

Meta has moved Catching Just-in-Time Tests (JiTTests) from research prototype into its production infrastructure. Meta JiTTests is an LLM-based system that writes executable tests designed to fail on a risky code change. A failing test is concrete evidence that a diff changed behavior. Meta team reports that JiTTests caught 74 privacy SEVs at the diff stage in the first half of 2026. The method is described in the FSE 2026 research paper ‘Just-in-Time Catching Test Generation at Meta&#821

Get smart on it

JiTTests is a system that uses large language models to automatically write tests designed to fail when buggy code changes are submitted for review, providing concrete evidence of problematic behavior before the code is deployed. Rather than simply reviewing code like traditional AI tools, JiTTests executes tests to demonstrate actual behavioral differences introduced by a change. The system caught 74 privacy-related security issues at the review stage in the first half of 2026, with engineers reporting a 60 percent true-positive rate, though the tool currently remains internal infrastructure not available to outside developers.

Read next
The biggest AI stories, once a day

One short email a day with the stories that matter. Free. Unsubscribe with one click.

Relevant courses

Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.

Browse AI courses on Maven
Related news
Agents & ProductsOpen story →

At Holiday Extras, dots get to work before anyone asks

Dots deliver launch reports unprompted, flag issues people might miss, and talk through upcoming meetings on the commute to work.

Agents & ProductsOpen story →

OpenAI wants to stop deepfakes from overwhelming child abuse tiplines

OpenAI is announcing a tool that it says will help child sexual abuse investigators cut through the noise to find harmful material they can act on quickly. At a Monday press briefing in Washington, DC, OpenAI announced a classifier it says can better detect abusive imagery of kids, including whether it's AI-generated. It's also offering free access to vetted organizations, giving developers more guidance on how to detect this type of content, and helping to train law enforcemen

Agents & ProductsOpen story →

Advancing computer-use agents for healthcare teams

Automating routine clinical tasks could free physicians and nurses to focus on patient care and complex decision-making.

Agents & ProductsOpen story →

More ways to move care forward with ChatGPT for Healthcare

Introducing computer-use agents, improved clinical answers, and new healthcare plugins that work across healthcare software to get real work done.

Agents & ProductsOpen story →

LVMH’s Media Division announces strategic partnership with OpenAI

LVMH’s Media Division and OpenAI announce a partnership to support journalism with AI and make its publications more accessible through ChatGPT.

Agents & ProductsOpen story →

Introducing ChatGPT Wallet

Introducing ChatGPT Wallet, a secure way for agents in ChatGPT Work, Codex, and dots to complete purchases with user approval and existing card protections.

Also reported by TechCrunch and The Verge