Anthropic Claude Cowork

Claude Cowork

Jason Poley Jan 19, 2026 3 min read
Claude AI

Claude Cowork is an autonomous desktop agent from Anthropic, released January 2026 as a research preview. It extends the capabilities of Claude Code — previously limited to developers working in the terminal — to general knowledge workers through a visual interface in the Claude Desktop app.

How It Works

Users grant Claude access to specific folders on their computer and describe tasks in natural language. Rather than providing instructions or suggestions, Cowork executes the work directly: reading files, creating plans, breaking complex tasks into parallel subtasks, and delivering finished outputs.

Typical tasks include file organization, document generation (Excel spreadsheets with formulas, PowerPoint presentations, Word documents), data extraction from PDFs and images, and synthesis of research across multiple files.

Security Architecture

Cowork runs inside an isolated virtual machine using Apple's Virtualization Framework with a custom Linux filesystem. This architectural separation means Claude can only access folders explicitly authorized by the user — the rest of the system is inaccessible at the VM level, not just by policy. Users can grant or revoke folder access at any time, and file processing occurs locally.

Availability and Limitations

Skills/Hooks Support

Cowork shares configuration with Claude Code. They use the same ~/.claude/settings.json and skills from ~/.claude/skills/.

Key Differences

Configuration Sharing

Claude Cowork shares configuration with Claude Code. It directly reuses ~/.claude/settings.json. This means same API keys, same base URL, same models, same behavior. Claude Cowork also auto-discovers skills from ~/.claude/skills/. GitHub

What Cowork Inherits

What's Different

Reuse of hooks

You can now use hooks inside skills prompts and subagents, which is extremely powerful.