In brief
- Google Cloud introduced the Gemini agent on Thursday, a single AI for work that runs in the cloud for hours or days and operates across Gmail, Docs, Sheets, Slides, Drive, Chat and Calendar.
- Managers can create "coworker agents" with their own Workspace email address, calendar, Drive storage and company directory listing, each tracked in an audit trail separate from any human.
- Google gave no pricing or general availability date; financial services and legal versions are in preview, with government, healthcare and retail listed as coming soon.
Google Cloud introduced a universal AI agent for the workplace on Thursday, one it says can take a goal, go off and do the work, and return with the finished result. CEO Thomas Kurian presented it at the company's Gemini at Work event, saying that "work now starts in the prompt window."
The product, simply called the Gemini Agent, works inside Gmail, Docs, Sheets, Slides, Drive, Chat and Calendar, and also reaches into Microsoft 365 and Slack. Google says it keeps running in the cloud after you close your laptop, so a single task can stretch across hours or days.
The most interesting feature is what Google calls coworker agents. A manager describes a role, such as events coordinator, and Gemini creates an agent with its own Workspace account: an email address, a calendar, Drive storage and a listing in the company directory.
This is similar to what other agentic frameworks have explored. For example Grok popularized it with Grok Bot, OpenAI did the same with GPT dots, and Hermes introduced its bots feature offering the same functionality.
The new agent connects to Salesforce, ServiceNow, Jira, Snowflake, BigQuery and any server that speaks Model Context Protocol, an open standard that works like a universal plug between AI and software. It also runs on more than Google's own models: Gemini currently orchestrates across Gemini and Claude models from Anthropic, routing each job to the one Google considers the best fit for quality and cost.
Letting software act on its own raises obvious safety questions, and Google's answer is to treat each agent like an employee. Every agent gets a cryptographically attested identity, a digital ID verified through cryptography, and every action lands in an audit trail attributed to the agent rather than a person.
→All agents run inside an Agent Sandbox, a walled-off environment meant to keep software away from the rest of a system, and all their traffic passes through Agent Gateway, which Google describes as an "AI network firewall." Containment has failed before: in July, researchers at Accomplish AI reported that the local mode of Claude Cowork could escape its Linux virtual machine on Macs and reach files on the host computer.
Cost is the other worry, since agents burn through tokens, the chunks of text that AI models read and write and that customers are billed for. Google says nearly 500 of its customers each processed more than one trillion tokens over the past year, and it added real-time spend caps: when a project hits its limit, the agent pauses until someone clicks to resume.
Google did not publish pricing or a general availability date for the Gemini agent. The financial services and legal versions are in preview, while government, healthcare and retail are listed as coming soon.