Google Cloud introduced Gemini agent at its Gemini at Work event on Thursday, positioning the tool as a persistent, cross-platform AI assistant that runs in the background across apps and devices4. Available within the Gemini Enterprise app, the agent maintains context in the cloud so users can start a task on one device and continue it on another without losing state.
Gemini agent operates autonomously across Google Workspace, Microsoft 365, Slack, and the command line, handling multi-day enterprise workflows that span research, document creation, and code generation on web, mobile, and desktop1,2. It supports several AI models.
The launch builds on a broader integration push. Google added seven Gemini MCP integrations to Workspace on September 15, 2026, connecting Gemini with Asana, Atlassian Rovo, HubSpot, Mailchimp, QuickBooks, monday.com, and Salesforce3. Those connectors are enabled by default for eligible users, with admins controlling access at the domain, organizational unit, or group level. Google said the connectors currently support read actions only.
Workspace Studio received a separate update on September 17 that added custom starters, webhooks, workflow steps, and action-capable integrations with tools including Asana, Jira, Salesforce, and Slack. Google cited adding a Jira comment as an example of the write-side capability. The combination means Gemini's connectors pull project context into Workspace apps, while Studio can trigger and modify work in external systems.
Inside Workspace itself, the agent works directly with Gmail, Drive, Docs, Sheets, Calendar, and other apps. Users chat with the agent and assign it tasks from a single interface.
ANALYSIS By extending Gemini agent into Microsoft 365 and Slack rather than confining it to Google's own productivity suite, Google Cloud is competing for the orchestration layer in mixed-vendor enterprise environments rather than treating its agent as a Workspace upsell.