Very cool.
1) How do you deal with timings? If a step includes clicking on a link or something that needs loading, then if you just fire off the generated playwright code at at once, some steps might fail because the xpath is not there yet. So to be safe, i'm guessing you would have to wait using the difference in the timestamps in the json.
2. For self healing, we worked on something similar, and we found it's very easy to get off the rails if one step fails because if your assertions of if the fix was correct are off, then the next and next steps will also fail etc. The most stable way was to just regenerate all steps if a step fails in 2 attempts (2 runs of the flow) consecutively. If the xpath is broken for a step, very likely the subsequent ones won't be worth healing individually.
1) we made this sick function in browser use library which analyses when there are no more requests going through - so we just reuse that!
2) yeah good question. The end goal is to completely regenerate the flow if it breaks (let browser use explore the “new” website and update the original flow). But let’s see, soo much could be done here!
1. Oh yes right. I remember trying it out thinking it was going to be brittle because of analytics etc but it filters for those surprisingly well.
2. We are working on https://www.launchskylight.com/ , agentic QA. For the self onboarding version we are using pure CUA without caching. (We wanted to avoid playwright to make it more flexible for canvas+iframe based apps,where we found HTML based approaches like browser-use limited, and to support desktop apps in the future).
We are betaing caching internally for customers, and releasing it for the self-onboarding soon. We use CUA actions for caching instead of playwright. Caching with pixel native models is def a bit more brittle for clicks and we focus on purely vision based analysis to decide to proceed or not. I think for scaling though you are 100% right, screenshots every step for validating are okay/worth it, but running an agent non-deterministically for actions is def an overkill for enterprise, that was what we found as well.
Geminis video understanding is also an interesting way to analyze what went wrong in more interactive apps. Apart from that i think we share quite a bit of the core thinking, would be interested to chat, will DM!
