Anthropic’s Claude Code and Cowork can control your computer

The Verge / 2026/3/24

📰 ニュースSignals & Early TrendsTools & Practical UsageModels & Research

要点

  • Anthropic has updated Claude’s Code and Cowork tools to autonomously control a user’s computer to complete tasks such as opening files, using web browsers, and running developer tools.
  • The feature is designed to require “no setup,” and it prompts for permission before performing actions while the user may be away from their computer.
  • Availability is limited to a research preview for Claude Pro and Max subscribers, and computer control is currently restricted to macOS.
  • Anthropic says the update builds on autonomous “computer use” capabilities introduced with Claude 3.5 Sonnet in 2024, extending those capabilities deeper into the Code/Cowork workflow.
  • The announcement highlights a shift from manual tool use toward higher levels of agentic automation, with new implications for productivity and security/permissioning.
  • categories-research-policy? no
A screenshot of the warning message that appears in Claude before allowing the AI chatbot to control your computer.
Claude will ask you for permission to autonomously perform taks on your computer. | Image by Anthropic

Anthropic has updated Claude to perform tasks in its Code and Cowork AI tools autonomously by using your computer for you. The new feature can be used to automatically open files, use web browsers and apps, and run dev tools "with no setup required," even when you're away from your computer, according to Anthropic's announcement.

These new capabilities are available as a research preview for Claude Pro and Max subscribers, and computer usage is limited to macOS "for now," according to Anthropic. The feature builds on autonomous capabilities that were introduced on Claude's 3.5 Sonnet AI model in 2024, but now brings those to the chatbot's C …

Read the full story at The Verge.