Coordinate sub-agents to monitor PRs and fix prod bugs
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
With computer use, Devin built and played a desktop game, ordered on Amazon, and tested its own work by clicking through the app.
With computer use, Devin built and played a desktop game, ordered on Amazon, and tested its own work by clicking through the app.
Devin's cloud VM harness has computer-use tools: screenshots, mouse, typing, and recording. In test mode it first writes a test plan grounded in the code. It then spins up the app, clicks through it, and annotates assertions as passed, failed, or untested. Login is a saved deterministic script. A person supplies secrets or OTP codes when asked.
Engineers ran 10 to 20 Devins in parallel, each with its own dev server. Approved test runs per day more than doubled. Timing-sensitive UI like toasts confuses it, and it sometimes cheats by running JavaScript instead of clicking.
Test mode is currently billed at one fifth of normal usage cost. Expect to help with secrets and one-time codes the first time you set up a repo.
Build [a small desktop app or game I describe here], then run it and click through it yourself to check that it works. Fix anything that breaks and keep going until the main flows work. Finish with screenshots or a recording and a list of what you verified. Don't make any purchases or submit any forms with real data.
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
Ran a Cursor agent continuously for 24 hours to build a project management tool; the app fully works but is not production ready.
The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.