Agentic AI

Computer Use

A capability that lets an AI agent operate general-purpose software by controlling a mouse, keyboard, and screen — reading the display, clicking buttons, and typing into fields on the user's behalf. Enables automation of workflows that lack APIs, such as legacy applications or complex web UIs.

Related terms

For developers

Call this framework and its tools from your own agent via the Model Context Protocol (MCP) server. Works with Claude Desktop, Cursor, Zed, Continue, and the OpenAI Agents SDK.

Where this fits

Computer Use is part of the Agentic AI vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.