Lenny RachitskyHost of Lenny's Podcast | Author of Lenny's Newsletter

"Codex reviews all of our PRs"

14 Feb 2026 · 1 min

Watch on YouTube

0:40

In this talk, the speaker explains how their team leverages OpenAI's Codex to automate code review and deployment workflows. Codex automatically reviews every pull request, cutting typical review times from 10–15 minutes down to 2–3 minutes for small changes, and often provides ready‑to‑merge suggestions that eliminate the need for a human reviewer. The team also built internal tools that use Codex to automate the steps required to get code into production, further collapsing engineering effort. The overall goal is to minimize manual work, allowing engineers to merge and ship far more frequently.

Chapters

The things that we tend to hand to the models immediately tend to be the things that annoy us or the most boring parts of software engineering. It's also why it's more fun. Now. Codex is really good at reviewing code. We create a lot of PRs, but Codex reviews all of them. And it makes code reviews go from a 10, 15 minute task to sometimes even just like a 2 to 3 minute task because you have a bunch of suggestions already baked in for small PRs you actually don't even need people to review. We kind of trust codecs in this way. If you talk to a lot of engineers, the thing that annoys me the most is after you've written your beautiful code, like, how do you get it into production? There's a lot of automated stuff you can do with Codex, and so we've actually built some tools internally that help automate that process. So all of that are trying to collapse into as little work for an engineer as possible, and the byproduct of which is they can now merge and push out a lot more peers.