Term
浏览器操作能力
Next Token / Wiki

Browser Use

Browser use is the ability of AI agents to complete tasks through a web browser: reading pages, clicking, filling forms and navigating. Browser Use is also the name of an open-source project that connects browser automation to LLM agents.

Also known as

browser automation

Definition

Browser use is the ability of AI agents to complete tasks through a web browser: reading pages, clicking, filling forms and navigating. Browser Use is also the name of an open-source project that connects browser automation to LLM agents.

How it works

The agent drives a real browser through browser automation protocols, converts the page structure into a representation the model can read, and loops: the model outputs the next action, the browser executes it, and the page state is fed back.

Usage

Typical uses include web research and price comparison, automated form filling and booking, authenticated in-browser workflows, and end-to-end web testing.

Compared with computer use, the scope is narrower but steadier: browser use operates only inside the browser, while computer use covers the entire desktop interface.

Sources