{
  "id": "computer-use-agent",
  "code": "PTL-0144",
  "term": "Computer-Use Agent",
  "aliases": [
    "computer use",
    "GUI agent",
    "browser agent",
    "browser use"
  ],
  "category": "agents",
  "definition": "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.",
  "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.",
  "example": null,
  "broader": [
    "ai-agent"
  ],
  "narrower": [],
  "related": [
    "multimodal-prompting",
    "human-in-the-loop",
    "indirect-prompt-injection"
  ],
  "introduced": 2024,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments",
      "authors": "Xie et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2404.07972"
    },
    {
      "title": "Computer use tool",
      "authors": "Anthropic",
      "year": 2024,
      "url": "https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool"
    }
  ],
  "url": "https://protologue.com/t/computer-use-agent/",
  "citation": "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/"
}