Small decisions. Interesting possibilities.Submit contentSubmit

How it uses Jev

Given a task and starting URL, Jev selects one browser action per step from the page’s clickable, typeable, and selectable elements. It also scores whether the goal is met or the run is stuck; code controls budgets, recovery, and stop gates.

What Jev decides

Goal reached?Example answers · not a recorded Jev response · Source ↗
Question 1 · goal done
YOUR APP
INSTRUCTION

Has the task's goal been achieved, based on the current page and history?

STATE

The navigation task, current page observation, and action history for the current browser step.

JEV · NOUL
YesNo

App workflow

  1. Start a run

    Provide a task and URL through MCP, CLI, or the `navigate` library function.

  2. Inspect the page

    Read the current page and enumerate available clickable, typeable, and selectable elements.

  3. Choose and execute a step

    Ask Jev to select a page action, then let the browser code execute it and repeat within configured limits.

  4. Stop and report

    Use goal and stuck scores plus code-owned stop gates, then return the final page and run artifacts.

Why it is interesting

It separates bounded action selection from the browser-control loop, and returns a trace, final page, console errors, and screenshot through MCP, CLI, or library entry points.