I’ve been experimenting with a similar approach using Playwright, and the biggest takeaway for me was how much “hidden API” most modern websites actually have.

Once you start mapping interactions → network calls, a lot of UI complexity just disappears. It almost feels like the browser becomes a reverse-engineering tool for undocumented APIs.

That said, I do think there’s a tradeoff people don’t talk about enough:

- Sites change frequently, so these inferred APIs can be brittle - Auth/session handling gets messy fast - And of course, the ToS / ethical side is a gray area

Still, for personal automation or internal tooling, it’s insanely powerful. Way more efficient than driving full browser sessions for everything.

Curious how others are handling stability — are you just regenerating these mappings periodically, or building some abstraction layer on top?