Gemini Can Now Control Your Mac, Completing Tasks for You

Google launched computer use in the Gemini Mac app, letting AI navigate native apps, files, and the web in the background while users keep working.

@sharedot

Gemini Can Now Control Your Mac, Completing Tasks for You

By @sharedot · · 6 pages

  • AI
  • Google
  • Gemini
  • Agents
  • Macos

Google launched computer use in the Gemini Mac app, letting AI navigate native apps, files, and the web in the background while users keep working.

What Google launched

Google announced that computer use is coming to the Gemini desktop application on macOS, allowing the AI to complete tasks on users' behalf, navigate native Mac apps, and browse websites in the background.

Users describe what they need, and Gemini handles the clicking, typing, menus, and forms across local files, desktop apps, and the web. The agent runs inside an isolated background window with a live preview in the chat, so the main screen and cursor remain free for other work.

Google says users can choose which apps Gemini can access, watch every step live, pause at any time, and approve key actions before they happen. The feature is initially available in English in the U.S. and requires the Gemini app for Mac plus a Google AI Plus, Pro, or Ultra subscription.

Why Google is late to the game

TechCrunch notes that Google is a little late to this launch, as other leading AI model makers like OpenAI, Anthropic, and Meta have already offered agentic features in their desktop applications for some time.

The move lands just as Google this week announced the broader rollout of Gemini's "Tasks," the in-app feature that lets the AI act more as an agent by signing into websites, making online purchases, or booking appointments.

Google also recently began admitting early testers to its revamped "CC" AI agent, announced in September, which is designed to help families stay organized across email, calendars, chats, and tasks.

Computer use adds a different kind of agentic offering — one that takes actions directly on the user's computer rather than through the web.

What it can actually do

Google suggests the feature suits tedious, repetitive workflows: filling out forms, repeating the same task across a batch of files, organizing files into folders by specific criteria, and creating slideshows from files or online dashboard data.

BetaNews offers more color on Google's examples, reporting that Gemini could batch color-grade photos or set up complex 3D scenes, extract weights, dimensions, and addresses from local PDFs to fill out multi-box shipping quotes, pull metrics and screenshots from live dashboards across multiple regions to build a presentation in Google Slides, and even analyze clothing photos from a folder, research pricing, and stage listings on resale platforms.

The company didn't say when the feature would expand to other markets or platforms.

Availability and the stakes

For now the feature is U.S.-only, English-only, and gated behind a Google AI Plus, Pro, or Ultra subscription, with the Gemini app downloadable from gemini.google › mac — and Google has not committed to a timeline for other markets or platforms, as BetaNews notes in its coverage of the update.

The stakes are about productivity positioning: Google is framing Gemini as a tool that saves time on repetitive work that normally takes dozens of clicks, transforming it from a chatbot into a hands-on productivity booster that frees users from waiting on prompts.

But because the agent acts directly on a user's machine — clicking, typing, and moving through menus and files — the approval and pause controls Google built in will likely face real scrutiny as the feature rolls out and users judge how trustworthy it is with their actual desktops.

Sources

  1. techcrunch.com › Google gives Gemini the ability to use your Mac for you
  2. betanews.com › Google Gemini can now be used to control your Mac

More on AI