I told windsurf to install playwright, identify crucial workflows of the app and add tests for them. Not without my input, but I got what I wanted without getting the hands dirty.
Does this thing add much on top?
Show HN: Web-eval-agent – Let the coding agent debug itself
11–13 of 13 posts
Re: Show HN: Web-eval-agent – Let the coding agent debug itself
#12I told windsurf to install playwright, identify crucial workflows of the app and add tests for them. Not without my input, but I got what I wanted without getting the hands dirty. Does this thing add much on top?
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.
Re: Show HN: Web-eval-agent – Let the coding agent debug itself
#13Gotta say, getting rid of all the clicking and checking just sounds like a huge win. I hate wasting time on all that.