AI product Open source
AutoBrowse is a browser-agent learning loop that improves task-specific behavior without changing model weights. It uses two Claude Agent SDK loops: a doer agent operates the browser, while a teacher agent reviews screenshots, traces, and task results after each run and writes lessons to a strategy.md file for the next attempt. When the strategy converges, the loop produces a reusable skill.md file containing site-specific navigation choices, waiting behavior, and other learned procedures that future agents can apply. The approach depends on replayable environments and verifiable outcomes, and the videos describe monitoring and failure-triggered repair loops for changing websites, with generated skills requiring review because of prompt-injection risks.
1 use taken from transcripts — each links to the moment in the video.
A hill-climbing loop for browser agents built on two Claude Agent SDK loops: a 'doer' agent that operates the browser and a 'teacher' agent that reads traces and screenshots after each run, writing lessons into a strategy.md file that carries into the next iteration. It converges on a reusable skill.md file so future agents start with learned site-specific tricks instead of from zero.
1 in the library.