Google Cloud Unveils Gemini Agent, a ‘Universal Agent for Work’

Google Cloud announced the Gemini agent on Oct. 8, 2026 at its Gemini at Work 2026 event, describing it as a “universal agent for work” that lives inside the Gemini Enterprise app, Google Workspace and third-party services.

According to Google, the pitch is that you “give it objectives, not instructions.” The agent can answer questions, handle knowledge work, create media, and write and run code — all from a single prompt box, the company says.

Google says the agent plans the work, uses skills and tools, connects to Cloud customers’ business systems, and returns something finished inside the documents, inbox and developer environments people already use.

How it works in Workspace

In Gmail, Docs, Sheets, Slides and Chat, you invoke it by mentioning @Gemini. 9to5Google gives the example of a manager emailing for a project update as a slide deck: Workspace Intelligence recognizes it as a delegatable task and offers a single-click option to pass it to Gemini.

The agent can also work without you naming anyone. Ask it to set up a meeting with the usual team of regional event leads next week, and Google says it works out who those people are from your chat space membership and your last event thread, checks their calendars, and starts an email thread to coordinate a time — even with external participants.

Beyond personal assistant duty, it can act as a “team member,” working on behalf of a group like a project manager, or on behalf of a role such as an analyst in a finance department.

Model choice, memory and sub-agents

Under the hood, the Gemini agent “runs each job on the model that fits best,” according to 9to5Google. That covers the Gemini and Claude families of models today, with support for other private and open models in the future, aimed at delivering “optimal quality and lower your costs.” It uses sub-agents to tackle multi-step tasks and connects to third-party tools, coordinating workflows with parallel and sequential steps that can run for hours or days.

The agent runs in the cloud for a “single set of memories, context, and one personalization graph.” 9to5Google lists four kinds of memory: session memory for the task at hand, semantic memory as a structured knowledge base, procedural memory for how a job gets done, and episodic memory of everything it has done before.

Google also says the agent has built-in cost controls plus the security, administration and governance enterprise customers require.

Availability

The Gemini agent is currently in private preview. 9to5Google reports it will see wide availability soon for Workspace customers on select Business and Enterprise plans. It is available from any device and channel — command line, Google Workspace, Slack and Microsoft 365 are given as examples — and an API lets it be integrated into third-party applications as a “headless agent” that does not need a dedicated user interface.

Related reading

Sources

• Google Cloud introduces the Gemini agent. — Google Blog
• Google Cloud announces ‘Gemini agent’ as ‘universal agent for work’ — 9to5Google