Small decisions. Interesting possibilities.Submit contentSubmit
fastbrowse GIF preview

fastbrowse

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

Added to Jevfast

How it uses Jev

When the page exposes more controls than fit in the next request, fastbrowse builds state from the task, subgoal, requirements, recent actions, and page identity. Jev evaluates whether each candidate control is relevant; code uses those Noul probabilities to shortlist controls before asking for the next action.

What Jev decides

Illustrative control relevance judgmentExample answers · not a recorded Jev response · Source ↗
Question 1 · r0
YOUR APP
INSTRUCTION

Is this candidate page element relevant to the next actions or information needed for the task? The element’s label, role, context, and link are included in the question.

STATE

A task and subgoal, outstanding information requirements, recent browser actions, page URL/title, and the shared relevance rubric. A candidate control is serialized into one per-control Noul question.

JEV · NOUL
YesNo

App workflow

  1. Observe the page and task

    Gather visible controls, page context, task requirements, and recent actions.

  2. Shortlist relevant controls

    When needed, ask Jev Noul questions about candidate controls and fit the most relevant set into the action request.

  3. Select a bounded operation

    Ask Jev to choose among currently available operations and controls.

  4. Verify and continue

    Code checks the action result and safety constraints before gathering the next observation.

Why it is interesting

The relevance pass is a bounded prefilter for browser controls, allowing the agent to spend its action request on more useful elements while keeping task policy and control execution in code.