More bro science, doesn't this have issues with plastics?

Would be happy to pay for this if I could write a prompt for how i want it to re-shape any page I visit! Like add specific instructions, etc.

This is awesome work - I can already imagine using this to hide features I don't want to see on websites at certain times.

Maybe I'm misunderstanding, but that is exactly what we do :)

Is anyone building 'Cursor for editing PDFs on the web'?

The power here is the coding agent has the ability to test visually if - and like a human would. So if the button isn't visible, the browser agent would use vision to detect that it's missing.

It sorta tests 'just like a human would' to make sure the flow that's implemented works as it's expecting to.

Yeah, I suppose to esafak's point, perhaps a benchmark for browser agent QA testing would be needed.

In browser MCP, looks like cursor controls each action along the way, but actually what we wanted was a single browser agent that had a high quality eval that could perform all the actions independently (browser-use)

We started with using browser-use because they had the best evals: https://browser-use.com/posts/sota-technical-report

- but we found that Laminar came out with a better browser agent (& a better eval): https://www.lmnr.ai/ so we're looking to migrate over soon!

Between steps it would preserve cookies, but atm when the playwright browser launches, it starts with a fresh browser state, so you'd have to o-auth to log in each time.

We're adding browser state persistence soon, hoping to enable it so once you sign in with google once, it can stay signed in on your local machine.

Oh okay thanks - that would be fire tbh