Prompting
Computer Use
A model capability that lets an AI operate a desktop the way a person does: it looks at screenshots and issues mouse and keyboard actions like click, type, and scroll.
In depth
A model capability that lets an AI operate a desktop the way a person does: it looks at screenshots and issues mouse and keyboard actions like click, type, and scroll. With Claude's computer use tool, the model never connects to the machine directly; your application executes each requested action in a VM or container and returns a screenshot or status. The loop repeats until the task is done. Because on-screen content can carry prompt injections, Anthropic recommends isolating the environment from sensitive data and getting user consent.
Primary source: platform.claude.com
Example
A model capability that lets an AI operate a desktop the way a person does: it looks at screenshots and issues mouse and keyboard actions like click, type, and scroll.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Prompting.
FAQ
Common questions
What is Computer Use?
A model capability that lets an AI operate a desktop the way a person does: it looks at screenshots and issues mouse and keyboard actions like click, type, and scroll.
Why does Computer Use matter for AI developers?
Computer Use sits in the Prompting part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Computer Use?
Developers Digest publishes tutorials and videos that cover Prompting topics including Computer Use. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
Prompting
Chain-of-Thought Monitoring
Chain-of-thought monitoring uses an automated monitor, often another language model, to read a reasoning model's chain of thought and flag signs that it intends to misbehave, such as reward hacking, sabotage, or deceiving the user.
Prompting
Reasoning Summaries
Readable digests of a reasoning model's internal chain of thought, returned in place of the raw reasoning.
Prompting
Reward Model
A model trained to give a response a single score that predicts how much a human would prefer it.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever