Lead story
Ask your AI
Top stories
Models & availability
Latest
Lead story
Ask your AI
Top stories
Models & availability
Latest
Cognition's Devin AI software engineer now autonomously verifies its work using computer use in the cloud, running tests in parallel. The company reports that for the first time, more Devin sessions are triggered asynchronously than interactively. To improve reliability, Devin writes test plans grounded in source code and uses deterministic scripts for common setup steps.
From the source
Devin will spin up the app, click through it, and confirm its changes actually work, the same way an engineer would.
cognition.com