Browser chores, done by an agent in Chrome
Browser chores are the jobs on sites that have no API: portals, dashboards and forms. With the Definable Chrome extension, an agent works beside you in Chrome's side panel. It reads the page, clicks, types and moves between tabs, only on sites you allow, and hands back to you when it needs you.
How it works in Chrome
- 01
Beside the pages you allow
The Chrome extension puts the agent in Chrome's side panel, and it acts only on the sites you allow in your browser.
Channels - 02
Clicks, types and moves between tabs
It finds elements by name, runs several steps at once, works inside embedded frames and reads a page's network requests.
- 03
Stays on its tab, hands back to you
The agent stays on the tab it started on, and when a step needs a person it hands the page back to you.
- 04
Searches the web too
Every agent can also search the web and read pages, and says which sites an answer came from.
Browser chores FAQ
Can an agent use the web?
Every agent can search the web and read pages, on by default. With the Chrome extension it can also work in your browser: read the page, click, type and move between tabs, only on sites you allow, and hand back to you when it needs you.
Where can I put an agent?
Slack, WhatsApp, Telegram, the Chrome extension and a web app that comes with every agent. More channels are on the way.
How do I start?
Sign up on the Free plan, add a key for one model provider, and ask Builder for your first agent.
Sign up free