Browser-use Agent
In one line
A browser-use agent is an agent that drives a real web browser — navigating sites, filling forms, even completing checkouts — and is becoming a default interface in AI search and shopping.
Going deeper
A browser-use agent operates a real web browser — opens the site, clicks the links, fills forms, and finishes the checkout. You can see it inside ChatGPT's agent mode, in browser-native products like Perplexity Comet and in the open-source browser-use project.
The message for marketers is clear: from now on, sites need to be friendly to both humans and bots. The more your experience depends on heavy JS rendering, captchas or non-standard forms, the more often agents will fail on your site.
Inside the GEO and agentic commerce stack, the browser-use agent is the bridge from 'AI search' to 'payment'. Getting cited is only half the work — the cited page also has to survive a bot clicking through it.
Related terms
Computer Use
Computer Use is the agent capability of perceiving the screen and driving the mouse and keyboard, letting an AI operate a computer the way a human would.
AI AgentAgentic Commerce
Agentic commerce is the emerging model in which AI agents handle the entire shopping flow — search, compare, decide, pay — on behalf of the user.
AI AgentUCP
UCP (Universal Commerce Protocol) is the AI-agent payment and checkout protocol Google introduced at NRF 2026, aimed at standardising how agents buy products on a user's behalf.
AI AgentAI Agent
An AI agent is an LLM-driven system that takes a goal, plans the steps, calls the tools it needs and runs the task end-to-end with limited human input.
AI AgentAgentic Search
Agentic search is the paradigm where an AI agent runs multiple searches and tool calls on the user's behalf, then synthesises a single answer.