Google 推出一站式 Gemini 工作任务 Agent
英文标题：Google is launching a one-stop Gemini agent for your work tasks
Google 宣布推出一款可在后台跨应用、跨设备工作的“通用”Gemini AI Agent，并将其集成至 Gemini Enterprise 应用。企业用户可通过单一界面与 Gemini 对话并分配任务，Agent 可覆盖 Gmail、Drive、Docs、Sheets、Calendar，以及 Slack、Microsoft 365 等第三方应用。该系统可调用面向特定岗位的子 Agent，并可作为拥有独立身份及“@agents.company.com”邮箱的“同事 Agent”运行。目前该功能仅面向企业客户开放私密预览，反映出 Google 希望将 Gemini 打造成统一工作入口的更广泛战略。
30.1 KB
197.3 KB
2.9 KB
307.8 KB
822.8 KB
1.4 MB
705.7 KB
207.0 KB
833.8 KB
206.4 KB
572.3 KB
1.2 MB
406.0 KB
212.5 KB
855.6 KB
86.0 KB
中文
Google 正在推出一款可在后台跨应用、跨设备工作的“通用”Gemini AI Agent。这项工具于周四的 Gemini at Work 活动上发布，将在 Gemini Enterprise 应用内提供，使用户能够通过单一界面与 Gemini Agent 对话并为其分配任务。
除了让 Gemini 直接在 Gmail、Drive、Docs、Sheets、Calendar 等 Workspace 应用中工作外，用户还可以通过移动设备、桌面电脑、网页以及 Slack 或 Microsoft 365 等第三方应用与该 Agent 交互。由于其运行于云端，Gemini 将在所有已连接设备之间保持相同的上下文。
Google 表示，Gemini 还可以与面向特定岗位的子 Agent 协同完成任务，并能够作为一名拥有专属身份及独立“@agents.company.com”邮箱的“同事 Agent”运行。Gemini 将自动使用最适合该项工作的 AI 模型来执行任务。
这款 Gemini Agent 目前仅向企业客户提供私密预览，但它或许展示了 Google 对 AI 助手的更广泛愿景：用户可从单一窗口提问，并让助手代为完成工作。Google 此前曾于 5 月推出面向消费者的 Gemini Spark Agent，订阅用户可利用它在 Workspace 和网页中执行任务；但该产品通过 Gemini 应用内一个独立的界面提供。
English / 原文
Google is launching a “universal” Gemini AI agent that can work across apps and devices in the background. The tool, announced as part of the Gemini at Work event on Thursday, will be available within the Gemini Enterprise app, allowing users to chat with the Gemini agent and assign it tasks from a single interface.
In addition to having Gemini work directly inside Workspace apps like Gmail, Drive, Docs, Sheets, Calendar, and others, users can interact with the agent from their mobile device, desktop computer, the web, and third-party apps like Slack or Microsoft 365. Since it runs in the cloud, Gemini will maintain the same context across all connected devices.
Google says Gemini can also work with job-specific sub-agents to complete tasks, as well as operate as a “coworker agent” with a dedicated identity and its own “@agents.company.com” email. Gemini will automatically perform tasks using an AI model that best fits the job.
The Gemini agent is currently only available to enterprise customers in private preview, but it may offer a glimpse into Google’s broader vision for the AI assistant that can answer questions and perform work for you from a single window. Google previously launched its consumer-facing Gemini Spark agent in May, which subscribers can use to perform tasks across Workspace and on the web, but it’s available through a separate interface within the Gemini app.