Launching today

UI Verify
Visual testing for coding agents
6 followers
Visual testing for coding agents
6 followers
UI Verify shows your coding agent every screen its change touched, so the agent catches and fixes its own UI bugs before your users see them. Used by teams at JetBrains, Cura and Metica. Works with Playwright, Storybook, Vitest and Bun, and with iOS and Android apps. Set up in one line. Free to start, and free for open source: 50,000 snapshots a month.






Free Options
Launch Team

Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing
Promoted
Hey Product Hunt 👋 I'm Igor, a product engineer in London, and I built UI Verify.
Coding agents check the page they changed. They don't check the dozens of other screens the same change touches, and that's where UI breaks slip through.
UI Verify shows your coding agent every screen its change touched, so the agent catches and fixes its own UI bugs before your users see them.
Adam Towers, CTO at Cura and a UI Verify customer, said: "A Tailwind refactor broke a bunch of our buttons. Now UI Verify catches those bugs before we ship, and otherwise stays out of the way. Awesome stuff."
Teams at JetBrains, Cura, Metica and others already use it.
UI Verify works with Playwright, Storybook, Vitest and Bun, and with iOS and Android apps too. To try it, open your coding agent in your repo and paste: Set up UI Verify in this repo: fetch https://uiverify.ai/install.md with curl and follow it.
It's free to start, and free for open source: 50,000 snapshots a month.
Run more agents. Break nothing.
the Tailwind refactor breaking buttons on screens nobody opened is the kind of bug that always slips through, becuase the agent only looks at the page it was asked to change
how do you handle changes that are on purpose??? does the agent update the baseline itself or does a human approve it first???