News

ToolsNov 19, 20263 min read1 source

Gemini can now take over your Mac to do multistep tasks

Worth watching

Google’s Gemini app can now control a Mac directly, organizing files and running tasks, but it’s US-only, English-only, and needs a paid plan.

Read it in

Drafted with AI· Nov 19, 2026

Tools · Nov 19, 2026

The distilled version

  • Google says its Gemini desktop app can now control a Mac directly: opening apps, browsing, and completing multistep tasks across files.
  • Google suggests the feature could help with repetitive jobs like filling forms, sorting files into folders, or building slideshows from existing data, and you can pause or approve each step.
  • It’s US-only, English-only, Mac-only, and needs a paid Google AI Plus, Pro, or Ultra subscription, so most teams should watch, not switch workflows yet.

What happened

Google announced on Thursday that its Gemini desktop app for macOS now has computer use: the AI can navigate native Mac apps and browse the web in the background to complete tasks on a user’s behalf, according to TechCrunch.

Google suggests the feature could be useful for multistep work across local files, apps, and the web, such as filling out forms, repeating a task across a batch of files, organizing files into folders by criteria, or building slideshows from dashboard data. Users see the agent work in a live preview inside the chat and can pause, stop, or approve its actions before they happen, while keeping their own screen and cursor free.

The feature is initially available in English in the US, requires the Gemini app for Mac, and needs a Google AI Plus, Pro, or Ultra subscription. Google has not said when it will expand to other markets or platforms. TechCrunch notes OpenAI, Anthropic, and Meta already offer similar agentic features in their desktop apps.

Why it matters

If your team works on Macs, this is a step beyond a chatbot that answers questions: it’s software that can actually click through your files and apps to finish a task. For small businesses, that could mean less manual file sorting or form-filling, but only once it’s available on your plan and language, and only for tasks you’re comfortable letting an AI touch directly.

What it means for your business

If you run the business: this isn’t urgent since it’s US, English-only, and tied to a paid Google AI subscription. Worth a look if your team is already on Google AI Plus, Pro, or Ultra and uses Macs, but don’t change workflows around it yet.

What to do

Worth watching
  • Check if your team’s Google AI subscription (Plus, Pro, or Ultra) already includes this, or if it would mean an upgrade.
  • If you have access, try it first on a low-stakes task like organizing a test folder of files, not live customer or financial data.
  • Keep the pause-and-approve step on for every action until you’ve seen it work reliably a few times.
  • Hold off on building any process around this until Google confirms it’s available outside the US or on other platforms.

Worth watching: no action needed yet; revisit when it matures.

Hype check

The claim: Google frames this as Gemini handling tedious work on your Mac for you.

The reality: It’s a new, US-only, English-only feature tied to paid plans, and competitors like OpenAI, Anthropic, and Meta already offer similar agentic features.

Jargon in this story

AgentAutomationHuman in the loop

Sources

  1. 1Google gives Gemini the ability to use your Mac for you (opens in a new tab) · TechCrunch · News report · Nov 19, 2026

Keep going: learn it, then do it.

03Automator8 min

Add an approval step before anything goes out

Design the pause: who approves, what they see, and what happens if nobody does.

Learn · 3 minTry it · 5 min
Start lesson
Agents & automation

What is an AI agent, really?

An AI that takes actions toward a goal, not just one that answers questions.

6 min