Computer Use: Definition and Examples
Ability of an AI model to directly interact with a computer by controlling the mouse, keyboard, and screen, just as a human user would.
Full definition
Computer Use refers to an advanced feature that allows an artificial intelligence model to take control of a computing environment. Concretely, the AI can see what is displayed on the screen via screenshots, move the mouse cursor, click on elements, type text on the keyboard, and navigate between different applications.
This capability represents a major paradigm shift in human-machine interaction. Rather than being limited to generating text or code, the AI becomes a true agent capable of executing complex tasks in a real graphical environment. For example, it can fill out a web form, manipulate a spreadsheet, use design software, or perform internet searches autonomously.
Computer Use relies on a perception-action loop: the model receives a screenshot, visually analyzes its content, decides on the action to perform (click, keystroke, scroll), then observes the result to plan the next step. This iterative approach allows managing multi-step workflows without constant human intervention.
Introduced by Anthropic with Claude in October 2024, Computer Use paves the way for automating repetitive tasks that previously required human intervention. It differs from APIs and traditional scripts because it interacts with existing graphical interfaces without requiring prior technical integration with the software used.
Etymology
The term 'Computer Use' is an English loanword that literally means 'use of the computer'. It was popularized by Anthropic when launching this feature for Claude in 2024. The choice of this simple name reflects the ambition: to allow AI to use a computer exactly as a human would, with no distinction between the two types of users from the machine's perspective.
Concrete examples
Automation of repetitive administrative tasks
Open the browser, log into our CRM, export the list of active clients from last month in CSV format, then send this file by email to the sales team.
User interface testing
Browse our website, test the complete registration process by filling in every form field, and report any display or usability issues you notice.
Web research and information synthesis
Search for the latest 5 news articles on European AI regulation, open each article, read the content, and produce a structured summary with sources.
Practical usage
In prompt engineering, Computer Use allows delegating tasks that involve graphical interfaces to the AI, without needing to develop API integrations. It is particularly useful for automating workflows that span multiple different software applications. For best results, describe the steps sequentially and precisely, indicating the exact names of buttons or menus to click on.
Related concepts
FAQ
What is the difference between Computer Use and Tool Use?
Is Computer Use reliable for critical tasks?
Which AI models support Computer Use?
See also
How to use this prompt
- Copy the prompt with the button above.
- Paste it into ChatGPT, Claude or your favorite AI assistant.
- Replace the bracketed variables with your details, then refine the result.
About Prompt Guide
Prompt Guide is a free library of 2500+ ready-to-use prompts for ChatGPT, Claude and other AIs, with guides to learn prompting and tools to build and optimize your own prompts.
More definitions
Custom GPT: Definition and How to Create Your Own
Understand OpenAI's Custom GPTs: pre-configured ChatGPT assistants. Step-by-step creation, differences with Claude Skills and Gemini Gems.
Embedding: Definition and Examples
An embedding is a numerical representation of text, image, or other data type as a vector of numbers, enabling AI models to measure semantic similarity between items.
Gemini Gem: Definition and Creation (Google)
Understand Google's Gemini Gems: preconfigured Gemini assistants. Creation, Google Workspace integration, comparison with Custom GPT and Claude Skills.
Gemini Pro: Definition and Examples
Gemini Pro is a multimodal language model developed by Google DeepMind, designed to handle complex tasks of reasoning, text generation,
Grouped Query Attention: Definition and Examples
Attention mechanism that groups multiple query heads to share the same keys and values, thereby reducing memory and computational cost during inference.
Model Registry: Definition and Examples
A Model Registry is a centralized system for storing, versioning, and managing machine learning models throughout their lifecycle, from training to production deployment.
Get new prompts every week
Join our newsletter.