Anthropic has launched the most ambitious consumer AI agent to date, giving its Claude chatbot the ability to directly control a user’s Mac—clicking buttons, opening applications, typing into fields, and navigating software on the user’s behalf while they step away from their desk.
Computer Use: From Conversation to Action
The new computer use feature, available immediately as a research preview for paying subscribers, transforms Claude from a conversational assistant into something closer to a remote digital operator. The feature arrives inside both Claude Cowork, the company’s agentic productivity tool, and Claude Code, its developer-focused command-line agent.
The computer use feature works through a layered priority system. When a user assigns Claude a task, it first checks whether a direct connector exists—integrations with Gmail, Google Drive, Slack, or Google Calendar. If no connector is available, Claude falls back to navigating Chrome via Anthropic’s browser extension. Only as a last resort does Claude interact directly with the user’s screen—clicking, typing, scrolling, and opening applications the way a human operator would.
When Claude does interact with the screen, it takes screenshots to understand what it’s looking at and determine how to navigate. This means Claude can see anything visible on the screen, including personal data. Anthropic trains Claude to avoid engaging in stock trading, inputting sensitive data, or gathering facial images, but the company acknowledges these guardrails “aren’t absolute.”
Dispatch: Your iPhone as a Remote Control
Paired with the new Dispatch feature, users can pair their mobile device with their Mac by scanning a QR code. From that point forward, they can text Claude instructions from anywhere, and Claude executes those instructions on the desktop while the user is away.
Use cases range from mundane to ambitious: having Claude check email every morning, pull weekly metrics into a report, organize a cluttered Downloads folder, or compile a competitive analysis from local files. Scheduled tasks allow users to set a cadence once—”every Friday” or “every morning”—and let Claude handle the rest.
Competitive Landscape
Anthropic’s timing is not accidental. The company is shipping computer use capabilities into a market reshaped by the rise of OpenClaw, an open-source framework that enables AI models to autonomously control computers. OpenClaw proved users wanted AI agents capable of taking real actions, spawning an entire ecosystem of derivative tools.
Nvidia entered the fray last week with NemoClaw, its own framework designed to simplify OpenClaw deployment with added security controls. Smaller startups like Coasty are also pushing into the space, marketing “full browser, desktop, and terminal automation.”
Early hands-on testing suggests the feature works well for information retrieval and summarization but struggles with more complex, multi-step workflows. One reviewer noted it works “about half the time”—and that may be the point, as Anthropic positions this as a research preview rather than a finished product.