# What is computer use (AI that controls a computer)?

Computer use is a capability that lets an AI model operate a computer the way a person does: it looks at screenshots and asks for mouse clicks and keystrokes, which your application carries out in an environment you control.

## How it works

The model never touches the machine directly. It returns actions such as "take a screenshot", "click here" or "type this" as [tool calls](https://ai-powered.com/academy/glossary/tool-call); your application performs them in a sandbox or virtual display and sends back the result.

## Why it needs care

Anthropic's docs warn that the model can follow commands it finds on screen, even when they conflict with your instructions: [prompt injection](https://ai-powered.com/academy/glossary/prompt-injection) at its most direct. They recommend a dedicated virtual machine or container with minimal privileges, no sensitive data or logins, an allowlist for internet access, and a person confirming anything with real-world consequences, such as payments.

## Sources

Official documentation, checked on 19 November 2026:

- [Computer use tool (Claude docs)](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool)

## Related terms

- [AI agent](https://ai-powered.com/academy/glossary/ai-agent): An AI agent is a system in which a language model decides, step by step, which tools to use and what to do next to finish a task, checking the result of each step before the next. A fixed script decides nothing; an agent directs its own process.
- [Prompt injection](https://ai-powered.com/academy/glossary/prompt-injection): Prompt injection is an attack where instructions meant for an AI are hidden in content it reads, such as a web page, email, document or a tool's result, to make it do something the user didn't ask for, like leaking data or misusing a connected tool.
- [Tool call](https://ai-powered.com/academy/glossary/tool-call): A tool call is a structured request from an AI model to run one of the functions it was given, with arguments that match the function's input schema. The app runs the function, sends the result back to the model, and the model uses it to answer or to decide its next step.
