AI MarketingVideo Blog4 min read

Your Next Coworker Has Its Own Email Address

November 10, 2026By Sandbox Media

Your new hire needs a desk, a login and a laptop. This one skips the laptop and gets an inbox. Google's Gemini at Work announcement on October 8, 2026 introduced coworker agents. Per Google's post, you describe a role, Gemini creates the agent, and it receives its own Workspace account: an email address, a calendar, Drive and a presence in the company directory.

The question isn't whether this works. It's what you settle before any agent gets an inbox: its job, the person who answers for it, and the day its account is turned off.

Key Takeaways

Its own account. Google's Gemini at Work post (October 8, 2026) describes a coworker agent that gets its own Workspace account, with an email address, calendar, Drive and a place in the company directory.
Works like a colleague. Colleagues work with it by adding it to a Chat space or @mentioning it. In Google's example, it can suggest edits and reply to comments under its own name in the version history.
Its own identity. Google says it acts under its own identity rather than yours and sees only what you share with it, and that every action Gemini takes is written to an audit trail attributed to the agent.
Controls, and gaps. Google says security admins approve each agent's permissions, and that you can set a hard spend limit on a project: if it's triggered, that project's agent pauses. The post does not say when coworker agents are available, what they cost, or whether a person signs off on each action.

What is a Google coworker agent?

Per Google's post, a coworker agent is created by describing a role. It receives its own Workspace account, including an email address, calendar, Drive and presence in the company directory. Colleagues work with it by adding it to a Chat space or @mentioning it.

How does it work with a team?

In Google's example, a marketing manager asks an events coordinator agent in a chat group to draft a launch readiness document, which it posts back to the group. Tagged in a document comment, it can suggest an edit and reply, appearing under its own name in version history.

What does Google say about security and access?

Google says a coworker agent acts under its own identity rather than yours and sees only what you share with it, and that every action Gemini takes is written to an audit trail attributed to the agent.

What should a business settle before using one?

Three things, before the agent sends its first email:

The job, in one sentence. If you can't write it, the agent isn't ready.
The person who answers for it. A named human, not "the team."
The day its account gets turned off. Pick the date now.

That's the practical move from the episode, not something Google's post prescribes. Need a starting point for the "who answers for it" part? Start with your company's AI policy.

What Google's post says, at a glance

Item	What Google's post says
Announced	October 8, 2026, Gemini at Work
Created by	Describing the role you need
Gets	Its own Workspace account: email address, calendar, Drive, directory presence
Works with the team via	Chat space, @mention, document comments
Identity and access	Acts under its own identity; sees only what you share with it
Controls	Security admins approve permissions; a hard spend limit set on a project pauses that project's agent
Availability and price	Not stated in the post

Frequently Asked Questions

When can I get it? Google's post does not say when coworker agents are available.

How much does it cost? Google's post does not give a price.

Does a person approve what the agent does? The post describes admin-approved permissions and a project-level spend limit that pauses that project's agent, but does not say whether a person signs off on each action.