Jev request structure for a browser agent, shown in an example
The author shows a real Jev request for a Browser Use scenario, with state holding the page and recent actions and questions asking for the operation, click target, input value, and whether the task is complete.
the Jev request ends up looking something like this: { "model": "jev-latest", "state": { "task": "...", "page": "...", "browser": "...", "recentActions": [] }, "questions": { "operation": "...", "click_target": "...", "input_target": "...", "input_value": "...", "goal_complete": "..." } } Here's a diagram of the loop.
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand executes it.
This post quotes another post: “ChatGPT co-inventor releases Jev, a model built for decisions rather than text”