Small decisions. Interesting possibilities.Submit contentSubmit

jev-browser, a general browser skill

We turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:

Added to Jevfast

How it uses Jev

The user gives an agent a website and task. The browser opens automatically, and Jev decides each click from what is visible on screen.

App workflow

  1. Provide a task

    The user supplies a website and goal.

  2. Open the browser

    The browser starts automatically for the website.

  3. Choose each click

    Jev selects clicks based on the visible screen.

  4. Continue toward the goal

    The browser skill applies those choices while working through the task.

Why it is interesting

It packages screen-based click decisions as a reusable browser skill for agents, so a task description can drive interaction across websites.