Jev 驱动浏览器 agent 的请求结构示例
作者展示 Browser Use 场景下 Jev 的实际请求体：state 带页面与近期动作，questions 里逐项问操作、点击目标、输入值与任务是否完成。
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.
这条是引用着另一条写的：「ChatGPT 联合发明人发布新模型 Jev」