JevMade Sign in
← Back to guides

JevMade field notes / Worked recipe

Let a browser assistant choose from visible actions

This browser recipe gives Jev a list of available controls and shows why an assistant's claim of success still needs an exact check.

Original by Jeroen Erne / NexibeoBrowser use

Listen to this guide

JevMade’s plain-English explanation

0:00 /

Our summary

This recipe builds a browser assistant that chooses among listed page actions instead of inventing where to click. Software reads visible links, buttons, and fields, then asks Jev which action best serves the user's goal. Password and file fields are excluded from the offered controls.

The program performs the chosen action using the control's recorded identifier and checks whether the page changed. Separate questions estimate whether the goal is complete or the assistant is stuck. Another text-generating model writes field values when typing is needed; Jev does not generate that text.

In one reported test, both the action choice and completion check accepted the wrong, similar-looking page. An exact destination check exposed the mistake. The author recommends keeping dangerous actions unavailable or behind human confirmation, and treating page content as potentially hostile instructions.

Key takeaways

  1. Let software define which page actions are available.
  2. Check the actual destination rather than trusting an AI success signal.
  3. Require permission before purchases, sending, deletion, or other consequential actions.

Page-control descriptions and surrounding text go to Jev, and another model writes typing values. Excluding password fields does not make other page or form data private.

GitHub cookbook

Read the original guide Opens the author’s site in a new tab.

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.