What is Computer Use?

Computer Use is Anthropic's production API that allows Claude to control computers through visual interface interaction. Unlike traditional AI integrations that require specific APIs or custom code for each application, Computer Use enables Claude to interact with any software the same way a human would.

The Paradigm Shift

Traditional automation requires:

• Custom API integrations for each service
• Maintaining code as UIs change
• Building separate solutions for each application

Computer Use changes this by letting Claude:

• See your screen through screenshots
• Understand what's displayed using vision capabilities
• Act by controlling mouse and keyboard

Key Capabilities

The Computer Use API provides Claude with these tools:

Tool	Purpose
computer	Take screenshots, move mouse, click, type, scroll
text_editor	View and edit files directly
bash	Execute terminal commands

Model Performance

Claude Sonnet 4.6 leads the OSWorld-Verified benchmark at 72.5% accuracy on real-world computer tasks, nearly matching Opus 4.6 (72.7%) and reaching the ~72% human baseline. This continues a steep improvement curve: Sonnet 3.5 scored 14.9%, Sonnet 4.5 reached 61.4%, and Sonnet 4.6 now sits at 72.5%.

Note: Computer Use is enabled via the computer-use-2025-01-24 anthropic-beta header — it is the stable production tool version as of 2026, not experimental. The header signals intent, not maturity. For safety, run agents in sandboxed environments (Docker, VM, or dedicated browser profile) regardless of stability level — the agent sees and can act on whatever your screen shows.

What You'll Build

Capstone preview — the Job-Form Filler. Every technique you learn across the next five modules stacks into this one real agent:

Module 1 → mental model of screenshot → vision → action
Module 2 → Docker sandbox + Agent SDK setup
Module 3 → Desktop automation (the window-opening half)
Module 4 → Browser automation (forms, auth, session handling)
Module 5 → Production safety (dangerous-action guardrails, audit logs)
Capstone → All of the above, wired together for real applications

Build checkpoint — do this before the next lesson

1. Collect 3–5 real job descriptions you might actually apply to. Save as .txt files in a jds/ folder. These are your capstone inputs.
2. Find 2 job-board form URLs you want the agent to fill. Public application forms (Greenhouse, Lever, personal career sites) work well. Private boards requiring login need Module 4's auth patterns.
3. Prepare your resume as a PDF at a known path. The capstone's file-upload tool needs an absolute path.
4. Install Docker Desktop if you haven't — Module 2 runs the agent in a sandboxed container so it can't damage your host system.

In the next lesson, we'll explore how Computer Use works under the hood. :::