Your coding agent can run all night. It still can't tell if what it built actually works. Today we're open-sourcing the TestSprite CLl (Apache-2.0) A tool your agent calls on its own to test your app end-to-end like a real user, fix what broke, and re-check everything it ever got right. It's the same engine 100,000+ teams already use. github.com/TestSprite/testsp… We proved it in public, on a public leaderboard: Most correct app on the board:89% Built by the cheapest model in the field At half the cost of the priciest one You no longer need the biggest, most expensive model to ship software you can trust. Setup is 2 commands: npm install -g @testsprite/testsprite-cli testsprite init That's the last command you'll ever type - from there, your agent runs the tests itself.

Thanks to the @sreday_com team for hosting us in SF last Friday! @yunhaojiao , our CEO, talked about what breaks when AI writes the code, and how TestSprite catches it by testing the running app end to end. Great meeting so many engineers who care about reliability.

Great to connect with AI founders at AWS Startup Day SF! The agenda ran from the agentic stack to security as a day-one choice. Agents keep changing apps. TestSprite makes sure those apps still work after every deploy. Thanks @AWSstartups for hosting 🤝

One of the clearest breakdowns we've seen on agent systems that survive production. The whole thing is worth reading, from cutting fake dependencies to designing failure as a local event. The part closest to our world is verification on the edge: "Do not ask the same agent to generate, approve, and publish its own work in one context. Separate the roles." That's independent verification in a sentence. A checker earns its place by producing nothing new, its only job is to stop weak work from reaching the user.