Test an iPhone game and report what passed
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.
Done withDevin
- What they did
- 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.
- How it went
- 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.
- Worth knowing
- The report's list of untested areas shows what the agent did not cover, so you still have to review those parts yourself.
Try it yourself with Devin
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.
Source: openai.com · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Generate internal dashboards and data migration scripts
A backend engineer says their team uses Devin for internal dashboards and migration scripts, treating output as a starting point that saves about four hours of boilerplate.
Build a Pong game and website from scratch
A tester asked Devin to create a basic Pong-style game and a website, and it finished both in under 20 minutes.
Play RollerCoaster Tycoon
Ramp Labs put Claude Code in RollerCoaster Tycoon.
Play Doom with computer-use agents as an informal benchmark
The OpenClaw team used computer-use agents to play Doom on remote machines, treating game performance as an informal way to improve the computer-use workflow.
Play a button-clicking game via a browser agent
A developer wired Gemini's Computer Use model to Playwright in Java and had it play a simple button-clicking game to verify click-coordinate scaling.