Google Launches Gemini AI Agent for Mac to Automate Computer Tasks
Google has released a significant update to its Gemini desktop application for macOS, introducing an AI agent capable of performing direct computer tasks. This new 'computer use' feature allows the AI to navigate native applications and websites to execute multi-step workflows, such as organizing files, filling forms, and creating presentations. Users retain control by approving actions via a live preview in a separate window. Currently available only in English for U.S. subscribers with Google AI Plus, Pro, or Ultra plans, this launch positions Google alongside competitors like OpenAI and Anthropic in the agentic AI space.
Editorial responsibility
- No named human review is recorded for this page.
- Reports are grouped by semantic similarity and deterministic rules. Language models may assist titles, summaries, translation and cross-source analysis; the page reads the event directly, while its address stays stable when the title changes.
- Summary covers the current reports
Cross-source coverage
Reporting timeline
Gemini App on Mac Gains Computer Task Automation Capability
The Gemini application for macOS has received a significant update enabling it to perform tasks directly on the user's computer. This new functionality addresses a top feature request from the user community, marking a shift towards more autonomous interaction with the operating system. The announcement highlights the integration of advanced AI capabilities into the desktop environment, allowing the model to execute actions beyond simple text generation or chat responses. This development positions the Gemini app as a more powerful tool for productivity and system management on Apple devices.
Read sourceGemini App for Mac Introduces Computer Use to Control Apps and Web
Google has launched a new 'computer use' feature within the Gemini app for Mac, enabling users to delegate complex tasks across folders, applications, and web browsers. This update allows the AI agent to actively click, scroll, and type within a live background window while the user retains control of their screen and cursor. The capability is designed to facilitate seamless task handoffs, such as transforming a quick sketch into a rigged 3D model directly within Blender software. By integrating these automation capabilities, the Gemini app moves beyond simple text generation to perform interactive operations on the user's desktop environment.
Read sourceGoogle Enables Gemini to Control Macs via Separate Window
Google has announced a new capability for its Gemini AI assistant, allowing it to control Mac computers on behalf of users. This feature operates within a separate window interface, distinguishing it from standard in-app interactions. The update represents a significant step in integrating generative AI directly into desktop operating system workflows, enabling the model to execute commands and manage tasks autonomously under user supervision. While specific details regarding the scope of control or security protocols were not provided in the source text, the announcement highlights Google's expansion of AI agent capabilities beyond simple chat interfaces into direct device management. This development positions Gemini as a more active participant in user productivity environments.
Read sourceShow 2 older updatesHide older updates
Google Gemini AI Agent Arrives on Mac to Organize Files and Automate Workflows
Google has released a significant update to its Gemini platform, introducing a dedicated AI agent for macOS. This new capability allows the system to autonomously perform complex tasks, including organizing digital files, filling out forms, and executing multistep workflows. The integration marks a shift from simple chatbot interactions to active agent-based operations within the desktop environment. By enabling the AI to interact directly with the operating system's file structures and input fields, Google aims to enhance productivity for users managing intricate digital tasks. This development represents a concrete step in the adoption of generative AI agents for consumer software applications.
Read sourceGoogle Launches Gemini AI Agent for Mac to Automate Computer Tasks
Google has announced a new update to its Gemini desktop application for macOS, introducing an AI agent capable of performing computer use tasks directly on the user's device. This feature allows the AI to navigate native Mac applications and websites to complete multi-step workflows, such as organizing files, filling out forms, and creating presentations. Users can instruct the AI via chat, view a live preview of its actions, and retain control by pausing or approving steps before execution. While this move positions Google alongside competitors like OpenAI and Anthropic in the agentic AI space, it arrives later than their existing offerings. The feature is currently available in English for users in the U.S. with a Google AI Plus, Pro, or Ultra subscription, though expansion to other markets and platforms remains unannounced.