# Computer-Use Agent

> A computer-use agent operates a graphical computer interface the way a person does, by looking at screenshots and issuing mouse clicks, keystrokes, and scrolls, so it can work with software that has no API.

- Identifier: PTL-0144
- Category: Agents & Orchestration
- Canonical URL: https://protologue.com/t/computer-use-agent/
- Also known as: computer use, GUI agent, browser agent, browser use
- Introduced: 2024

## Description

The agent loop alternates between a screenshot and an action until the task is done. Benchmarks such as OSWorld measure performance on real desktop tasks. Because these agents read arbitrary on-screen content, they are exposed to prompt injection from web pages and documents, so they are run in isolated environments with human confirmation for sensitive actions.

## Broader terms

- [AI Agent](https://protologue.com/t/ai-agent/)

## Related terms

- [Multimodal Prompting](https://protologue.com/t/multimodal-prompting/)
- [Human-in-the-Loop](https://protologue.com/t/human-in-the-loop/)
- [Indirect Prompt Injection](https://protologue.com/t/indirect-prompt-injection/)

## Sources

- Xie et al. (2024). OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. https://arxiv.org/abs/2404.07972
- Anthropic (2024). Computer use tool. https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool

## Cite this entry

Protologue. (2026). Computer-Use Agent. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0144). https://protologue.com/t/computer-use-agent/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)