Google Brings Gemini Computer Use to Mac, Letting Its AI Handle Multi-Step Desktop Tasks
Google has added computer-use capabilities to its Gemini app for Mac, allowing the assistant to navigate selected desktop apps, local files and websites in a separate window. The English-language rollout is initially limited to the United States.

Google is adding computer-use capabilities to its Gemini app for Mac, giving the AI assistant the ability to carry out multi-step tasks across desktop applications, local files and websites. Announced on November 19, the feature is designed to handle repetitive work such as filling forms, organising files and assembling presentations from information spread across different sources.
Rather than simply suggesting steps, Gemini can interact with a Mac interface by clicking, typing and navigating menus. Google says the activity takes place in an isolated background window, with a live preview visible in the chat. This allows a user to continue working on the main screen while the assistant carries out an approved workflow.
How Gemini's computer-use feature works
A user describes a task in the Gemini Mac app and selects which applications the assistant is allowed to access. Gemini can then move through those apps and websites to complete the requested sequence. Google's examples include extracting information from local PDF files to fill out shipping forms, batch-editing photographs, organising files into folders and preparing presentation material from live dashboards.
The feature is intended for workflows that involve multiple actions rather than a single question. For example, a user might ask Gemini to review a group of files, collect specified details and enter them into a form. The assistant can perform the navigation and data entry while showing its progress in a live preview.
User permissions and oversight remain central
Google says users choose which applications Gemini can access and can watch its actions as they happen. They can pause or stop the process, and the system asks for approval before key actions. The separate window is designed to keep the assistant's activity visible without taking over the user's main screen or cursor.
These controls matter because an AI agent that can operate software has a different risk profile from a chatbot that only returns text. Actions in files, applications and websites can have consequences, so users should review the requested permissions, supervise sensitive workflows and check results before relying on completed actions.
Initial rollout is limited by region and device
At launch, computer use is rolling out in English in the United States through the Gemini app for Mac. Google's announcement specifies an Apple Silicon Mac running macOS Sequoia 15.0 or later, and access for eligible personal Google accounts held by adults using Google AI Plus, Pro or Ultra plans.
The company has not announced a wider country rollout or a date for availability on Windows. That means Mac users in India and other markets should not assume the feature is available to them yet, even if they can use the Gemini desktop app for other functions.
Why desktop AI agents are becoming a bigger contest
Computer-use tools are part of a broader shift from conversational assistants towards agents that can act across software. They promise to reduce repetitive clicking and copying between applications, but their usefulness depends on reliability, clear permissions and the ability to recover when a workflow goes wrong.
Google is entering a field where other AI providers have already introduced desktop agent capabilities. The company's approach emphasises an isolated work window, visible progress and user approval. Those safeguards will be important as people test whether the system can handle real tasks consistently rather than just demonstrate them in controlled examples.
What to watch next
The next milestones will be the feature's expansion beyond the United States, support for additional operating systems and the range of applications it can use reliably. Google has not given a public timetable for those changes. For now, the launch is a geographically limited step towards making Gemini more than a question-and-answer assistant on the desktop.
Sources
Related stories

US Tightens AI Chip Restrictions, Raising Concerns for Alibaba and Tencent
New US export rules target remote access to advanced American computing chips through overseas data centres, closing a route Chinese technology firms used to obtain AI computing power. Alibaba says the measures could affect some global data-centre expansion plans, while Tencent warns that tighter access may slow future model development.

Sarvam AI Faces Sovereignty Debate Over Chinese Models on Token Factory
Indian AI startup Sarvam is facing questions about its sovereign-AI positioning after adding Chinese-developed models to its Token Factory inference platform. The company says the service runs on privately procured GPUs in India and is intended to give local developers access to a wider choice of models.

A leaner 5G connection moves closer to everyday sensors and wearables
Ericsson and Altair Semiconductor say they have completed the first eRedCap network connection, a step towards lower-cost, lower-power 5G devices for sensors, trackers and connected wearables.

Small Businesses Get an AI Campaign Assistant as InMobi Unveils Accelerate
InMobi has introduced a self-serve advertising platform that uses seven specialised AI agents to help small businesses and agencies plan, build and optimise campaigns across major ad networks from one dashboard. Advertisers retain approval control over campaign plans, creatives and budgets.
