OpenAI makes Auto-review free in Codex, the second agent that checks risky actions

OpenAI has made Auto-review free. It is the Codex feature (Codex is the OpenAI coding agent) in which a second agent reviews what the first one does. It is now free for everyone who signs in with a ChatGPT account and no longer draws usage from their plan. Thibault Sottiaux, who works on Codex and ChatGPT, announced it in a post on X on Tuesday, October 6.

Codex works inside a set of limits, the sandbox (the bounded space where it can act without asking for permission). When it needs to go beyond them, for example to reach the network or edit files outside the allowed folders, it asks for approval. With Auto-review, that request does not wait for a person: another agent reviews it, decides whether the action runs and explains why.

According to Sottiaux, its only goal is to prevent high-risk actions and actions that do not match what the user originally asked for. That makes it possible to run long tasks without approving everything by hand, which he says leads to decision fatigue unless you spend a lot of time configuring specific rules. It can be turned on in Settings > Permissions > Auto-review.

OpenAI states in its documentation that Auto-review does not give the agent more permissions, it only changes who reviews actions that already needed approval, and that it is not a deterministic security guarantee.

It arrives on day two of the 28-day challenge Sottiaux announced on Sunday: each day, either a clear improvement for most Codex or ChatGPT Work users (ChatGPT Work is the ChatGPT agent for more ambitious tasks) or, failing that, a full reset of usage limits. On day one, Monday, GPT-6 Astra and GPT-6.1 Sol started responding about 50% faster.