Google Gemini Can Now Control Your Mac, Open Apps and Complete Tasks With New AI Feature

Google Gemini Can Now Control Your Mac, Open Apps and Complete Tasks With New AI Feature

Google has introduced computer use capabilities in its Gemini desktop app for macOS, allowing the AI assistant to operate applications, navigate websites and complete tasks across a user's computer. Launched on November 19, the feature is rolling out in English to U.S. subscribers on Google AI Plus, Pro and Ultra plans, expanding Gemini's ability to perform actions beyond its chat interface.

The new capability allows Gemini to interact directly with Mac applications and local files, handling workflows that would otherwise require users to move between programs and complete individual steps manually. Rather than simply providing instructions, the assistant can navigate menus, enter information, interact with websites and carry out a sequence of actions based on a user's request.

Google has designed the feature to operate independently of the user's active desktop. Gemini performs its assigned tasks in a separate background window, with a live view of its activity displayed inside the conversation. This allows users to follow the assistant's progress while continuing to work with their own mouse, keyboard and applications.

The approach differs from automation that takes control of the main screen. Users can continue writing emails, editing documents or working in other applications while Gemini handles a separate assignment.

Google highlighted several potential uses, including completing online forms, organizing documents and processing large groups of files. The assistant can also assemble presentations using local materials or information from online dashboards, helping users complete tasks that involve multiple sources.

Other examples include preparing online listings for items being sold and repeating the same operation across numerous files. These workflows can require several actions across different applications, making them more involved than the individual requests typically handled through an AI chatbot.

The feature also includes controls intended to keep users informed about what Gemini is doing. Permissions are granted separately for individual applications, allowing users to determine which programs the assistant can access.

Users can monitor the AI's activity through the live preview, interrupt a task or stop it entirely. Gemini can also request approval before performing certain actions, giving users an opportunity to review its intended steps before allowing them to proceed.

These safeguards are particularly relevant because computer use gives an AI assistant the ability to interact with software and information beyond the chat window. Limiting application access and requiring confirmation for certain operations provide users with ways to supervise automated activity.

The launch builds on Google's broader effort to make Gemini capable of completing tasks on behalf of users. Earlier this week, the company announced expanded access to Gemini Tasks, which can assist with activities such as signing into websites, purchasing products and arranging appointments.

Google has also been developing CC, a separate AI agent introduced in September to help families coordinate information across email, calendars, messages and task lists. Early testers have recently begun receiving access to that service.

The new Mac functionality extends those agent-based capabilities to desktop applications, where Gemini can work directly with files and software rather than relying exclusively on connected online services.

Google first introduced its Gemini application for macOS in April 2026 and expanded its automation capabilities with Spark and Tasks in June. Computer use represents another step in that development, giving the assistant a way to perform actions across the desktop itself.

The company is entering an area where competing AI developers have already introduced similar functionality. OpenAI and Anthropic have offered desktop automation capabilities, while Meta has also been developing AI agents designed to act on users' behalf.

Google's approach emphasizes background execution, allowing the assistant to complete assignments without occupying the user's primary workspace. The combination of a separate operating window, real-time activity preview and application-specific permissions is intended to make automated tasks easier to monitor and control.

For now, availability remains limited. Users need the Gemini desktop application on macOS and an eligible paid Google AI subscription. The initial rollout supports English in the United States, with no announced timetable for additional countries, languages or operating systems.

The release gives Gemini users a way to delegate repetitive computer tasks while remaining active in other applications. Its usefulness will depend on how reliably the assistant handles real-world software, particularly workflows involving several programs and actions that require user approval.

With computer use, Google is extending Gemini from an assistant that helps users plan and understand tasks into one that can carry them out directly on a Mac, while keeping users involved through permissions, monitoring and approval controls.

This analysis is based on reporting from TechCrunch & Crypto Briefing.

Image courtesy of Google.

This article was generated with AI assistance and reviewed for accuracy and quality.

Updated Nov 19, 2026

About this article: This article was generated with AI assistance and reviewed by our editorial team to ensure it follows our editorial standards for accuracy and independence. We maintain strict fact-checking protocols and cite all sources.

Word count: 768Reading time: 0 minutes

AI News Daily

Breaking Intelligence • Since 2023

Join hundreds of thousands of AI professionals who start their day with our curated newsletter. Get breaking news, expert analysis, and exclusive insights.

Stay Ahead of AI

Get the latest AI breakthroughs, tools, and insights delivered to your inbox every week.

✓ Free forever✓ Unsubscribe anytime✓ No spam guarantee

Go Premium

Unlock unlimited AI tools and an ad-free reading experience designed for AI professionals.

• Ad-free experience• Premium AI tools
Start Free Trial

14-day free trial • Cancel anytime
Plus $9/mo • Pro $90/yr (2 months free)

Follow Our Community

ChatAI

Breaking Intelligence

Your daily briefing on what matters in AI. Trusted by developers, researchers, executives, and AI enthusiasts worldwide.

© 2026 ChatAI. All rights reserved.