I use AI agents to build UI features daily. The thing that kept annoying me: the agent writes code but never sees what it actually looks like in the browser. It can’t tell if the layout is broken or if the console is throwing errors.

So I built a CLI that lets the agent open a browser, interact with the page, record what happens, and collect any errors. Then it bundles everything — video, screenshots, logs — into a self-contained HTML file I can review in seconds.

  proofshot start --run "npm run dev" --port 3000
  # agent navigates, clicks, takes screenshots
  proofshot stop

It’s not a testing framework. The agent doesn’t decide pass/fail. It just gives me the evidence so I don’t have to open the browser myself every time.

Open source and completely free.

Website: https://proofshot.argil.io/

How does this compare to raw https://github.com/vercel-labs/agent-browser ?

Everyone is comparing this to Playwright but it's solving a different problem. Playwright checks structural properties, like does element X exist, is it visible, etc. That's useful but it can't tell you whether the page actually looks right.

I built something similar that takes a screenshot and uses a multi-modal LLM to evaluate it against a design mock. It catches a completely different class of error. The DOM can be structurally perfect and still look nothing like what was intended. Colors wrong, layout shifted, spacing off, components overlapping. No amount of DOM assertions will catch that.

These are two different kinds of gates: structural which are fast and deterministic, and stochastic which are slow but catch things that are completely different. There is very little overlap between the issues, and you want to catch both.

That way I can invest a lot of time getting the mock just right, then let the agents "make it so".

This would be _extremely_ valuable for desktop dev when you don't have a DOM, no "accessibility" layer to interrogate. Think e.g. a drawing application. You want to test that after the user starts the "draw circle" command and clicks two points, there is actually a circle on the screen. No matter how many abstractions you make over your domain model, rendering you can't actually test that "the user sees a circle". You can verify your drawing contains a circle object. You can verify your renderer was told to draw a circle. But fifty things can go wrong before the user actually agrees he saw a circle (the color was set to transparent, the layer was hidden, the transform was incorrect, the renderer didn't swap buffers, ...).

What does this do that playwright-cli doesn't?

https://github.com/microsoft/playwright-cli

I've always found screenshots on PRs incredibly helpful as a reviewer. Historically I've had mixed success getting my team to consistently add screenshots to PRs, so this tool would be helpful even for human code.

At work, we've integrated claude code with gitlab issues/merge requests, and we get it to screenshot anything it's done. We could use the same workflow to screenshot (or in this case, host a proofshot bundle of) _any_ open PR. You would just get the agent to check out any PR, get proofshot to play around with it, then add that as a comment. So not automated code reviews, which are tiresome, but more like a helpful comment with more context.

Going to try out proofshot this week, if it works like it does on the landing page it looks great.

seems similar to a couple of simonw's recent tools?

https://simonwillison.net/2026/Feb/10/showboat-and-rodney/

It looks similar to agent-video, which is also based on agent-browser: https://www.mux.com/blog/agentic-video-screen-recording

I don't think you need either, though, because agent-browser itself has a skill for this: https://github.com/vercel-labs/agent-browser/blob/main/skill...

Maybe the author would like to compare the three.

I'm currently experimenting with running a web app "headless" in Node.JS by implementing some of the DOM JS functions myself. Then write mocks for keyboard input, etc. Then have the code agent run the headless client which also starts the tests. In my experience the coding agents are very bad at detecting UX issues, they can however write the tests for me if I explain what's wrong. So I'm the eye's and it's my taste, the agent writes the tests and the code.

VSCode and Antigravity already do this. What am I missing?

I built something like this for native application, so that I could get automated feedback loop for the agent instead of making screenshots manually etc. Problem I found is that AI agent understands nothing of the UI. If you tell it "Make buttons evenly spaced", sure it will space them evenly, but without care for the context they are placed in. You have to describe the image yourself and still you'll find it having hard time understanding what's going on. I very much abandoned the idea of AI driven UI development as it is not there yet. I tried with GPT 5.2. Maybe newer models have improved.

I find the official Chrome DevTools MCP excellent for this. Lighter than Playwright, the loop is shorter, and easy to jam into Electron too.

I've been using playwright-cli (not mcp) for this same purpose. It lacks the video feature, I guess. But at least is local and without external dependencies on even more third parties (in your case, vercel). Perhaps you could allow to use a local solution as an alternative as well?

I use AI agents to build UI features daily. The thing that kept annoying me: the agent writes code but never sees what it actually looks like in the browser. It can’t tell if the layout is broken or if the console is throwing errors.

I give agent either a simple browser or Playwright access to proper browsers to do this. It works quite well, to the point where I can ask Claude to debug GLSL shaders running in WebGL with it.

I'm going the opposite of everyone else is saying.

This is sick OP based on what's in the document, it looks really useful when you need to quickly fix something and need to validate the changes to make sure nothing has changed in the UI/workflow except what you have asked.

Also looks useful for PR's, have a before and after changed.

I usually ask Claude Code to setup a software stack that can build/run whatever I am working on. Then I let it browse a website or navigate through screens. I also use Playwright to get screenshots of the website I am building. For e.g. apps or whatever application you are building, there should be a way to get screenshots too I guess.

Added benefit is that when Claude navigates and finds a bug, it will either add them to a list for human review or fix it automatically.

Pretty much a loop where building and debugging work together;-)

Once Claude Code

How would this play with mobile apps?

I'd love to see an agent doing work, then launching app on iOS sim or Android emu to visually "use" the app to inspect whether things work as expected or not.

I use the Claude Chrome extension for this. Works wonderfully. It lets Claude click through features itself, etc.

This is really cool. Have you thought of maybe accessing the screen through accessibility APIs? For Android mobile devices I have a skill I created that accesses the screen xml dump as part of feature development and it seems to work much better than screenshots / videos. Is this scalable to other OS's?

This is actually interesting. Feels like we’re moving from “generate UI” to “validate UI,” which is a completely different problem. Curious how you handle edge cases where something looks correct but breaks in interaction?

Slightly Off-topic of Agentic...

Anyone recommend browser-base instant preview site for web ui design with more artistic/experimental preference?

This is basically what antigravity (Google’s Windsurf) ships with. Having more options to add this functionality to Open code / Claude code for local models is really awesome. MIT license too!

This is awesome, does it work with desktop application ?

Thanks! I do share screenshots and paste them manually for front end stuff, nice idea though.

Looks nice! Does it work for desktop applications as well, or is this only web dev?

I am fed up of getting gaslit by coding assistants. "Your AI agent says it's done." really is a problem! Nice packaging here.

I built something similar[0] a few months ago but haven't maintained it because Codex UI and Cursor have _reasonable_ tooling for this themselves now IMO.

That said there is still a way to go, and space for something with more comprehensive interactivity + comparison.

[0] - https://magiceyes.dev/

what about mcp cdp ?

my claude drive his own brave autonomously, even for ui ?

This is really useful thank you!

I see

Gemini on Antigravity is already doing this.

Great to see this but exe.dev (not sponsored but they are pretty cool and I use them quite often, if they wish to sponsor me that would be awesome haha :-]) actually has this functionality natively built in.

but its great to see some other open source alternatives within this space as well.

That is not UI, that's just some web pages with JS.

Taking screenshots and recording is not quite the same as "seeing". A camera doesn't see things. If the tool can identify issues and improvements to make, by analyzing the screenshot, that's I think useful.