AIsaAIsaStudio English 打开 AIsa Studio

Google 为 macOS 版 Gemini 桌面应用加入 computer use 智能体功能

原标题:Google gives Gemini the ability to use your Mac for you

Google 宣布在 macOS 的 Gemini 桌面应用中加入 computer use 功能,AI 可代表用户操作本地 Mac 应用并在后台浏览网页,完成跨本地文件、应用和网页的多步任务,用户可通过聊天中的实时预览观看操作过程,且屏幕和光标仍可继续自己的工作;用户可暂停、停止或在执行前批准操作。该功能目前仅在美国以英语提供,需要 Gemini for Mac 应用及 Google AI Plus、Pro 或 Ultra 订阅,官方未说明扩展到其他市场和平台的时间。

为什么值得看

原文交代了功能范围、订阅门槛和可用地区,可与 OpenAI、Anthropic 桌面端的已有智能体功能做对比阅读。

阅读原文 ↗

本页的摘要、推荐理由与解读出自 AIsa Studio 的 AI 风向智能体,原文版权归原作者所有。

原文

Google on Thursday announced that it is bringing computer use to its Gemini desktop application on macOS, allowing its AI to complete tasks on users’ behalf, navigating native Mac apps, and browsing websites in the background.

The tech giant is a little late to the game with this launch, as other leading AI model makers like OpenAI, Anthropic, and Meta have already been offering agentic features in their desktop applications for some time. Meanwhile, Google only this week announced the broader rollout of Gemini’s “Tasks,” the in-app feature that allows the AI to work more as an agent, helping users sign into websites, make online purchases, or book appointments.

Google also only recently began admitting early testers to try its revamped “CC” AI agent, announced in September, which is designed to help families stay organized across email, calendars, chats, and tasks.

Computer use is another type of agentic offering that allows an AI agent to take actions directly on the user’s computer — in Gemini’s case, a Mac. This allows the AI to complete multistep tasks that involve getting things done across local files, apps, and the web. After the user instructs the AI what they want to do, they’ll see the agent working in a live preview in their chat, while still keeping their screen and cursor free to continue working on other things.

As with other AI agents offering computer use, users can pause, stop, and approve Gemini’s actions before they happen.

Google suggests the feature could be useful for tedious tasks and other workflows, like filling out forms, repeating the same task over and over across a batch of files, organizing files into folders based on specific criteria, creating slideshows from files or information in online dashboards, and more.

The feature is initially available in English in the U.S. and requires the Gemini app for Mac and a Google AI Plus, Pro, or Ultra subscription. The company didn’t say when it would expand to other markets or platforms.

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Sarah has worked as a reporter for TechCrunch since August 2011. She joined the company after having previously spent over three years at ReadWriteWeb. Prior to her work as a reporter, Sarah worked in I.T. across a number of industries, including banking, retail and software.

You can contact or verify outreach from Sarah by emailing [email protected] or via encrypted message at sarahperez.01 on Signal.

View Bio

原文版权归 TechCrunch · AI 及原作者所有,本站转载仅供阅读。如需删除,请联系 support@aisa.one。

事件综述

macOS 版 Gemini 推出 computer use 功能

2026 年 11 月 19 日,Google 宣布为 macOS 版 Gemini 桌面应用加入 computer use 功能。该功能可让 Gemini 跨本地文件/文件夹、桌面应用和网页执行多步骤任务,例如加速工作流、填表、制作演示文稿、上架待售物品;官方演示展示了 Gemini 在后台窗口中点击、滚动和输入,将一张草图变成 Blender 中带绑定的 3D 模型,操作过程可在聊天中的后台窗口实时预览。执行期间用户的屏幕和光标仍归自己掌控,可继续工作;用户可暂停、停止或在执行前批准操作,并决定 Gemini 能访问哪些应用。功能推出范围方面,据 TechCrunch 报道,该功能目前仅在美国以英语提供,需要 Gemini for Mac 应用及 Google AI Plus、Pro 或 Ultra 订阅,官方未说明扩展到其他市场和平台的时间。The Verge 报道同样称该功能以英语面向美国用户推出,但未提及订阅要求。

其他来源的报道 3