Cognition had Devin on GPT-6 Astra test the game Otter Run in a simulator, returning a recording and a report of checks passed and untested areas.
Cognition had Devin on GPT-6 Astra test the game Otter Run in a simulator, returning a recording and a report of checks passed and untested areas.
Devin, Cognition's cloud agent, ran on GPT-6 Astra and tested Otter Run, an iPhone game, in a simulator. It produced two outputs: a recording of the game running, and a report listing the checks that passed and the areas it left untested. Engineers use those outputs to see how the software behaves and what still needs attention.
The source gives no pass counts or timings. It presents the example as a step toward engineers reviewing less code by hand, which Cognition expects over time and has not yet shown.
The report's list of untested areas shows what the agent did not cover, so you still have to review those parts yourself.
Test my iOS app [app name] in the simulator. Play through [key flows, e.g. launch, first level, pause, game over] and record a screen recording while you do it. Finish with a report listing each check that passed, each failure with steps to reproduce, and areas you did not test. Don't change any code.
Claude Code got an old DirectX game running on modern hardware, decompiled much of it, built a headless parallel runner, and now writes full level guides with screenshots.
A Slack watcher starts a Devin session on each new client message to investigate, create a Linear ticket, draft a response and route follow-ups.
Josh gave Devin a card, phone, inbox, Stripe and repo to start a business; after four weeks and 10,929 calls it landed its first paying customer.