Computer use
Also: computer-use, browser agent, browser use
An AI system using screen controls. It can click, type, and move through applications, within the access it has.
The fuller definition
Computer use lets an agent operate software through screenshots, clicks, and typing, including a web browser, instead of through a programmed interface.
- ObserveRead the task, the current state, and the last result.
- DecidePropose the next action: a search, a file read, a calculation.
- ActThe harness runs the action, if permitted.
- CheckStop condition met? If not, loop again.
The model proposes; the surrounding software executes and records. Where the loop may act, and when it must stop and ask, are decisions made outside the model.
A concrete example
An agent opens a filing portal, fills in a form, and stops before submission so a person can review it.
The distinction that matters
Screen-level control reaches anything a person could click, so permissions, sandboxing, and approval gates matter more, not less.
Related terms
AI agent
An AI system that takes steps to do a task. It may choose tools, search, or work with files. Its access should have clear limits.
Agents & automationApproval gate
A point in an automated task where it must stop and wait for a person to say yes.
Agents & automationSandbox
A sealed-off space where an AI or a program can run without touching your real files or systems.
Where it is taught
Build your first agent around a document inventorySource and further reading
Anthropic · Building effective agentsThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.