Cognition applies GPT-6 Astra so Devin can test and prove its work

OpenAI published a customer story saying Cognition is applying GPT-6 Astra across Devin Cloud, CLI, and Desktop so the coding agent can test its work and return evidence.

A customer story puts Astra on Devin’s evidence loop across cloud, command line, and desktop, which is a workflow claim you can quote.

OpenAI published “Cognition helps Devin test its own work with GPT-6 Astra.” That customer story is the primary. It is not Cognition’s SWE-2 model launch, which is a different product post.

OpenAI says Cognition is applying Astra — OpenAI’s model — across its lineup: the core cloud agent that is Devin, plus the command-line interface (CLI) and the desktop app. The page’s through-line is test-and-prove evidence, not a new coding-model scoreboard.

Walden Yan, Cognition co-founder, on OpenAI’s page: one of the big pieces Astra improves on is its ability to test and prove that its work actually functions the way you expect. Cognition’s named problem on that page is review catching up as teams write more code.

OpenAI’s example: Devin uses Astra to test the iPhone game Otter Run and returns a recording of the game running in a simulator plus a report of checks that passed and areas left untested. Yan said that when a customer sends a screenshot of a bug, the team can pass it to Devin through Astra and get back a screenshot of the fixed result. Those workflows and the “review less code / ship more” direction are Cognition’s account on OpenAI’s page — not measured review-time cuts.