Takeaway: On November 19, 2026, Google introduced computer use in the Gemini app for Mac. You can describe a multi-step task, and Gemini can click, type, open menus, and fill in forms across local files, desktop apps, and the web. It runs in an isolated background window with a live preview in chat, so your main screen and cursor stay free. The rollout is in English in the United States, for personal Google accounts belonging to people 18 or older who have a Google AI Plus, Pro, or Ultra plan, on an Apple Silicon Mac running macOS Sequoia 15.0 or later.
The details below come from that Google blog post, by Michael Friedman, Group Product Manager for the Gemini app, and from Google’s help article Use Gemini to work with apps on your Mac. This article does not add countries, plans, or prices that those pages do not state.
What computer use does
Google’s post says computer use helps you get multi-step tasks done across local files, desktop applications, and the web. You describe what you need, and Gemini handles the clicking, typing, menus, and forms. It works inside an isolated background window, with a live preview in your chat. Google says your main screen and cursor remain completely free, so you can keep typing, designing, or taking calls without interruption.
You stay in control. The blog says you choose which apps Gemini can access, watch every step live, pause at any time, and approve key actions before they happen. The help article adds that Gemini moves the work onto a virtual screen so you can keep using other apps, and that you can open a full-screen preview or click Stop task to end the work.
Google’s examples, from the November 19 post, include:
- Batch color-grading photos in design software, or setting up complex 3D scenes.
- Extracting weights, dimensions, and addresses from local PDFs to fill out multi-box shipping quotes.
- Pulling metrics and screenshots from live dashboards across multiple regions and building a presentation in Google Slides.
- Analyzing clothing photos in a local folder, researching pricing, logging item details, and staging listings on resale platforms.
The help article gives a similar set of starter tasks, such as finding receipts in your Downloads folder and filling out an expense report, importing trip photos into Lightroom and exporting them as 4K PNG files, or finding a background image in a browser and setting it as your desktop wallpaper.
Who can use it, and how to turn it on
Computer use is rolling out in English in the U.S. in the Gemini app for Mac. Google’s blog says to download the app at gemini.google/mac. The stated hardware and account requirements are an Apple Silicon Mac running macOS Sequoia 15.0 or later, a personal Google account, age 18 or older, and a Google AI Plus, Pro, or Ultra subscription. The help article repeats those plan names as Gemini AI Ultra, Google AI Pro, or Google AI Plus.
The help page also says this is, for now, only available in Gemini tasks for personal accounts, not work or school accounts. For better quality responses, it suggests choosing Gemini Hydrogen 4 or newer models. That model family is separate from the Gemini 4 Neon launch earlier this week; this article does not treat computer use as a Neon-only feature, because Google’s help text is “Hydrogen 4 or newer.”
To turn it on, open the Gemini app on your Mac, go to Gemini Settings (or press ⌘ + ,), open Computer use, and make sure “Allow Gemini to work with your Mac” is on. If they are not already on, the help article says to turn on Accessibility and Screen & System Audio Recording. You can also enable “Use on-demand file backups.” Google says Gemini will try to create a temporary backup while it works, but is not always able to do so. Backups are kept for 24 hours, or until the next prompt, and you can review them from the chat under View backups. Content in some apps may not be backed up, depending on that app’s settings and permissions.
In a chat, the help article says to click Task below the chat box, mention @Computer use, and explain what you want Gemini to do. The first time Gemini needs an app, it will ask whether to deny, allow, or always allow permission. “Don’t allow” or “Allow once” applies only to that step or chat. “Always allow” adds the app to the Allowed apps list in Computer use settings. You can also pre-allow or block apps in those settings. Gemini can control only the apps you grant it access to.
How this differs from Gemini Tasks
This is not the same feature as Gemini Tasks becoming free in six countries. That earlier change was about scheduled and recurring tasks, and about which plan tiers could use them in those countries. Computer use is a Mac-app capability: Gemini operates desktop apps and websites on your computer, in a separate window, when you ask it to. The help article places computer use inside Gemini tasks on the Mac, for personal accounts only, but the product being announced on November 19 is the computer-use control itself.
What Google says about the risks
Google’s help article is explicit that agentic features can make mistakes and do unexpected things. Among the official cautions: Gemini can share information with desktop apps, not just websites; it can use logged-in accounts and active sessions inside native Mac apps, not only Chrome; some actions are irreversible even if Gemini tries to create backups; untrusted content on screen in one app can cause Gemini to take action in other allowed apps; granting access to code or text editors and developer tools can enable shell execution or broader file-system changes; Gemini may read or interact with multi-factor authentication prompts or codes that are visible in desktop or messaging apps; and automating some third-party apps may conflict with those apps’ terms of service. You are responsible for choosing which apps you let it use. For sensitive tasks, Gemini will ask for confirmation before continuing. Google also documents broader Gemini privacy controls separately, including the chat history and training controls announced this week.
Key facts
| Item | What official sources say |
|---|---|
| Announcement | Google blog post on November 19, 2026, by Michael Friedman, Group Product Manager, Gemini App. |
| What it is | Computer use in the Gemini app for Mac: multi-step clicking, typing, menus, and forms across local files, desktop apps, and the web. |
| How it runs | In an isolated background window, with a live preview in chat. Your main screen and cursor stay free. |
| Controls | You choose app permissions, watch a live preview, can pause or stop a task, and approve key actions before they happen. |
| Availability | Rolling out in English in the United States. Download the app at gemini.google/mac. |
| Requirements | Apple Silicon Mac, macOS Sequoia 15.0 or later, personal Google account, age 18 or older, and Google AI Plus, Pro, or Ultra. |
| Account type | The help article says this is, for now, only available in Gemini tasks for personal accounts, not work or school accounts. |
| Suggested model | The help article recommends Gemini Hydrogen 4 or newer models for better quality responses. |
| Backups | Optional on-demand file backups, kept for 24 hours or until the next prompt. Google says Gemini will try to create them but cannot always do so. |
FAQ
What is Gemini computer use on Mac?
It is a feature in the Gemini app for Mac, announced on November 19, 2026. You describe a task, and Gemini can click, type, navigate menus, and fill in forms across local files, desktop apps, and the web, in an isolated window with a live preview.
Who can use Gemini computer use?
Google says it is rolling out in English in the United States for personal Google accounts belonging to people 18 or older who have Google AI Plus, Pro, or Ultra, on an Apple Silicon Mac running macOS Sequoia 15.0 or later. The help article says it is not available for work or school accounts at this time.
Is computer use the same as Gemini Tasks?
No. Gemini Tasks is the scheduled-task product, including the recent change that made Tasks free in six countries. Computer use is the Mac capability that lets Gemini operate apps and websites on your computer. The help article places computer use inside Gemini tasks on the Mac, but it is a distinct capability.
How do I turn computer use on?
In the Gemini app for Mac, open Settings, go to Computer use, and turn on “Allow Gemini to work with your Mac.” Google also tells you to enable Accessibility and Screen & System Audio Recording if they are not already on. Then start a task, mention @Computer use, and grant app permissions when asked.
Can I keep using my Mac while Gemini works?
Yes. Google says Gemini works in an isolated background window, with a live preview in chat, and that your main screen and cursor remain free. You can watch the preview, open it full screen, pause, or click Stop task.
Does Gemini need permission for each app?
Yes. The first time it needs an app, it asks you to deny, allow, or always allow access. You can also maintain Allowed apps and Blocked apps lists in Computer use settings. It can control only the apps you grant it access to.
Does Google mention any risks?
Yes. The help article says Gemini can make mistakes, can use logged-in sessions in native Mac apps, may not always be able to create backups, and can be influenced by untrusted on-screen content. It also warns that access to developer tools can enable broader system changes, and that visible multi-factor authentication codes may be in scope if those apps are allowed. For sensitive tasks, Gemini asks for confirmation first.
Where do I download the Gemini app for Mac?
Google’s announcement points to gemini.google/mac. Computer use is a feature of that Mac app, not a separate download described in the blog post or the help article cited here.

Leave a Reply
You must be logged in to post a comment.