Google Cloud发布Gemini Agent

Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements:

• Gemini, a single, universal agent for work that answers your questions, handles your knowledge work, creates your images and media, and writes and runs code.
• Inline in Workspace, Gemini works directly inside Gmail, Drive, Docs, Slides, Sheets, Chat, and Calendar, carrying the same memory, skills, and controls it has everywhere else.
• New data and analytics skills that allow both technical teams and everyday business users to use plain-language questions to get to actionable operational insights in minutes.
• Industry-specific specialization with tools, skills, connectors and knowledge specific for financial services and legal teams.
• How we secure and govern agents through identity and policy management, authorization and permission controls, secure sandboxing, network gateways, and more.
• Leading cost controls through multi-model orchestration, Smart Routing, real-time spend caps, and more.
• Customer use cases that showcase the breadth and depth of our customers around the world.

Bringing the best technology to all of you is what drives us at Google Cloud. In the last year, nearly 500 Google Cloud customers each processed more than one trillion tokens. Today, nearly 80% of all Google Cloud customers are using our AI products, and nearly 90% of the Fortune 100 use Gemini Enterprise. At that kind of scale, organizations have moved past experimentation and are running their business on it.

Work now starts in the prompt window.

To meet this moment, today we are excited to announce the Gemini agent: your new single, universal agent for work. It has all of your business context and can be used for everything from knowledge work to answering questions, and from content creation to coding, all from a single prompt box. It plans the work, uses skills and tools, connects to your systems, and brings back something finished — inside the documents, the inbox, and the developer environments you already work in. It chooses the best model for the job, has built-in cost controls, and most importantly, has the security, administration, and governance required by your company.

The Gemini agent is your new single, universal agent for work.

Introducing the Gemini agent

Gemini answers your questions, handles your knowledge work, creates your images and media, and writes and runs code — all in a single agent and a single API. You give it objectives, not instructions. You delegate an outcome and come back to finished work. For an agent to do that, it has to be connected to your personal workflows, your systems of record, and your enterprise controls. Gemini can function as your personal assistant or as a team member, where it works on behalf of a group of people, like a project manager within a team, or on behalf of a specific role in an organization, like an analyst in your finance department.

The agentic capabilities in Gemini are built around core architectural principles:

• Unified agent: Gemini is an agent that can answer your questions when you chat with it, work autonomously to complete objectives you assign it, and generate code — all from a single interface. You can assign it work, schedule tasks that need to be completed, or have it respond to events.
• Omnipresent access: Gemini can be accessed from any device including web, iOS and Android mobile devices, Windows and Mac desktops, and any channel (command line, Google Workspace, Microsoft 365, or Slack). It can also be integrated into third-party applications and surfaces and operates as a headless agent, meaning it does not need a dedicated user interface.
• Persistent execution: It runs in the cloud, meaning it maintains a single set of memories, context, and one personalization graph no matter what device or channel you access it on. You never have to re-brief it or wonder which machine you told it to do something on. Work that takes hours or days keeps running after you close your laptop, and it is still there when you come back.
• Multi-agent orchestration: Gemini doesn’t work alone. It can dynamically create a roster of sub-agents — temporary, job-specific agents, each with their own identity — to tackle multi-step tasks. Gemini can communicate with these sub-agents to coordinate workflows, including parallel and sequential steps that can run for hours or days. In addition, Gemini can act as a coworker agent — which is more like a team member, with a persistent, defined role and operational presence across days, sessions, and multiple changing responsibilities — and delegate and coordinate tasks. Coworker agents have dedicated identities including their own @agents.company.com emails, their own persistent storage, and only have access to the context that you or your team members provide.
• Deeply contextual: Gemini arrives already knowing your tools, data, and work history. Whether you ask it a question, assign it an objective, or have it generate code, Gemini learns from every interaction with you. The longer you collaborate with it, the better it understands you and how you work. Teams can create dedicated projects to further optimize the context, skills, and tools Gemini uses when it works with you.
• Model choice flexibility: Gemini is the agent, and the model underneath it is a separate choice. It runs each job on the model that fits best — orchestrating across our Gemini family of models and Claude models from Anthropic today, and other leading private and open models in the future — to deliver optimal quality and lower your costs. The best model for the task is not always the largest one. Matching the model to the work raises accuracy on the difficult jobs and lowers cost on the simple ones. And the leading model changes every few months, so keeping that choice open means your context, your skills, and your data stay put when it does.

Top customers across industries were early testers and are already realizing its benefits: Premium sportswear brand On tested this new dynamic selection capability to accelerate its speed-to-market. This builds on the proven, large-scale multi-model strategies already used by leaders: Shopify blends frontier models for millions of merchants to unlock data and drive sales, and PayPal routes 10 million multi-model requests every week.

Powering Gemini: Skills, tools, and context

Gemini understands your business — everything from pricing to product portfolios to departmental norms — and all the institutional knowledge that makes your company unique. Three capabilities make that possible: tools that connect it to your systems, skills that teach it how your work gets done, and context that lets it remember.

• Tools and tools registry: Gemini can securely connect to the software your company already runs, including collaboration tools like Confluence, Microsoft Office, Teams, Slack, and Workspace; development tools like Git and Jira; enterprise platforms like Salesforce and ServiceNow; databases like BigQuery, Databricks, Postgres, and Snowflake; and files on your own desktop. It can also connect and work securely with any Model Context Protocol (MCP) server inside or outside your company network. It also offers an enterprise tools registry, so teams can build and publish tools for the rest of the company.
• Skills and skills registry: Skills are reusable sets of instructions, knowledge, or workflows stored as modular prompts that teach agents how to perform specific, multi-step tasks. Gemini ships with a robust global library of skills. Teams or departments can build and publish custom skills to a shared company registry, and you can build your own personal skills. Gemini chooses the right skills and tools to perform a task and continuously learns from each execution, improving its consistency, while saving token costs.