# Gemini agent Universal work agent announced on October 8, 2026 for research, content and code. Google describes shared enterprise context, tools and persistent cloud execution. Canonical profile: https://agenten-kompass.mmeierhoff.chatgpt.site/en/agents/gemini-agent/ Editor: [Michael Meierhoff](https://agenten-kompass.mmeierhoff.chatgpt.site/en/about/) Sources reviewed: 2026-10-09 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Gemini agent combines research, content and code in an enterprise context. The Gemini product family also includes Gemini CLI for terminal tasks and Gemini Spark for personal tasks. - Provider: Google - Product family: Gemini - Profile type: Announced universal cloud agent - Environment: Announced for web, desktop, mobile devices, Workspace and other channels - Connections: Announced: Workspace, Microsoft 365, Slack, enterprise systems and MCP - Setup: Confirm rollout and enterprise access; configure data sources and permissions - Pricing model: No dedicated public plan is yet documented for the announced Gemini agent ## Operation & oversight Operational details for this profile have not yet been researched. ## Provider Google Cloud develops the Gemini agent for enterprise work. It connects Gemini models with Workspace, enterprise data and administratively managed tools. - Operator: Google - Organization: Technology company - Website: https://about.google/ - Reviewed: 2026-10-09 - Provider source: https://about.google/company-info/ - Provider source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ## Prices and included usage Pricing checked: 2026-10-09 The universal Gemini agent was announced on 8 October. The announcement does not state a dedicated public plan. Gemini Code Assist and Agent Platform prices cover other products and are not listed here as Gemini agent prices. Pricing details: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ## Key features ### Plan work Google describes goal-based task planning. Source: https://blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/gemini-at-work/ ### Skills and tools Reusable skills connect workflow steps with tools. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Persistent execution Announced cloud execution keeps longer tasks running. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Permissions and logs Google describes agent identities, access policies and audit logs. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Generate code and content The announcement covers coding and content creation. Source: https://blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/gemini-at-work/ ### Coordinate temporary subagents Splits multi-step work across specialist subagents with their own identities. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Work as a persistent coworker Describes team agents with a dedicated role, email address and persistent storage. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Respond to schedules and events Start tasks on a schedule or in response to events; cloud context persists across devices. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Work in Workspace and other channels Announced interfaces include Workspace, Microsoft 365, Slack, CLI, apps and an API. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ## Requirements and limits ### General access remains unconfirmed Not yet confirmed: The release describes features and architecture but provides no complete rollout and pricing plan for all interfaces. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Dedicated identities for coworker agents Requirement: Coworker agents have their own email addresses and storage. Their work context comes from information provided by people or teams. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ### Enterprise policies for tool access Requirement: Identities, authorization, sandboxes and network gateways are the documented controls for access to enterprise systems. Source: https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 ## Example workflows ### Prepare a status report - Your input: Approved project documents and a reporting brief. - Possible result: Editorial example: a draft report. - What to check: Review sources, claims and recipients. ### Delegate analysis - Your input: A bounded question and accessible data. - Possible result: Editorial example: an analyzed question. - What to check: Review data permissions, calculations and results. ## Context Features reflect the 8 October announcement. Coworker agents receive dedicated identities; assigned context and central policies constrain enterprise data access. Official Google announcements dated October 8, 2026. Access and pricing for a specific deployment require confirmation. ## Sources - https://cloud.google.com/blog/products/ai-machine-learning/welcome-to-gemini-at-work-2026 - https://blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/gemini-at-work/ [Sources and method](https://agenten-kompass.mmeierhoff.chatgpt.site/en/sources/)