Jev browser agent searches Google Flights in 7 seconds
Reading the page as a numbered element table and picking a single operation from it cut Jev's browser calls from 1,092 to 101 and median time from 9.45s to 7.09s; the repo is open source.
A BROWSER AGENT SEARCHED GOOGLE FLIGHTS ZURICH → LONDON IN 7.1 SECONDS It was given one goal: search Google Flights for a flight from Zurich to London, with no site-specific scripts or screenshots The page gets read as a numbered element table, JEV picks one operation from there, click, type, select, scroll, wait, done or blocked It picks the element in the same request, so there’s only one round trip A small LLM only writes text when the operation is type_text The model never writes a selector, coordinate or JS, it only picks from what’s already on the page The same policy opened a Wikipedia article in 2.8s 9.45s → 7.09s median 1,092 browser calls → 101 The main difference comes from reducing how much the model has to do Fewer calls, smaller choices Worth stealing even if you never build browser agents Give the model a list of possible actions and make it pick instead of asking it to write the action itself Repo is open source, link below
This post quotes another post: x.com/noisyb0y1/status/2102309802072272956