Gemini Agent
Multi-step tasks, handled
The next step in building towards a universal AI assistant is here–navigating the complexities of your daily tasks, while keeping you in control. Gemini Agent makes a plan, then combines advanced features like live web browsing, deep research capabilities, and seamless integration with some of your Google apps to execute that plan on your behalf.
Your day, simplified
Manage your inbox by asking Gemini to create tasks, archive emails, and even draft a response for you to review, edit and send.
Browse it, book it, buy it
Gemini can do all the time-consuming research and live web browsing to gather information across multiple sites, compare options, and even help you complete bookings.
How Gemini Agent works
Leveraging Gemini 3, our most intelligent AI model
Gemini leverages our most capable AI model and brings together tools like deep research capabilities, and Canvas to chart the best course of action.
Bringing live web browsing capabilities
Gemini can use live web browsing capabilities to research and compare options across the web to complete your task.
Supporting complex actions with Google apps
Gemini connects to some of your favorite Google apps, like Gmail and Calendar, so you can easily manage your inbox and schedule.
Frequently asked questions
Gemini Agent is available with Gemini 3 Pro.
Gemini Agent is rolling out on web to Google AI Ultra subscribers in the US who have their language set to English. It is currently limited to Gemini users over the age of 18. Workspace and Student accounts cannot access Gemini Agent at this time. We look forward to expanding the experience to more regions and additional languages soon.
Gemini Agent can leverage some connected apps like Gmail, Google Calendar, Google Drive, Keep, Tasks, and it can also use Google Maps and YouTube services. You decide which connected apps to connect Gemini to and can manage your settings at any time.
Gemini Agent is an experimental feature in early development. As we continuously work to improve, your supervision is important to help prevent unintended and potentially harmful actions. To help reduce possible risks associated with the use of AI agents, Gemini Agent includes features designed to support safer use and mitigate the likelihood of unintended or potentially harmful actions. Learn about how we address these risks for Gemini Agent.
Select Agent from the tools in the prompt bar to get started. From there, just describe your task or goal in your own words. Think about to-dos that require:
Managing your inbox, calendar, or other Google apps.
Planning multi-step projects, like a trip or an event.
Researching, summarizing, and acting on information from the web.
Handling online bookings, reservations, or purchases.
Check responses. Subscription and setup required. Compatibility and availability varies. Available to users 18+.