Google is expanding its AI capabilities beyond conversation. Its Gemini Tasks feature can help users sign in to websites, make purchases and book appointments, while its new computer-use capabilities allow AI to work directly across a Mac’s applications, files and browser.
Users can assign Gemini multistep tasks, monitor its progress through a live preview in the chat and continue using their computer while the agent works. They can pause or stop the process at any time, as well as approve actions before they are completed.
Follow THE FUTURE on LinkedIn, Facebook, Instagram, X and Telegram
From Repetitive Work To Multistep Tasks
The feature is designed for time-consuming workflows such as filling out forms, repeating operations across multiple files, organising documents into folders based on specific criteria and creating slideshows using files or information from online dashboards.
By automating these tasks, AI agents could become more than conversational assistants, helping users complete work across the applications and services they already use.
Availability And Access
Computer use is initially available in English in the US. Users need the Gemini app for Mac and a Google AI Plus, Pro or Ultra subscription. Google has not announced a timeline for availability in other markets or on additional platforms.
The launch follows the introduction of CC, an AI agent designed to help households manage emails, calendars, chats and everyday tasks. The product was announced in September.







