What is Google Agentspace?

Google Agentspace is an intranet search, AI assistant, and agentic platform, bringing knowledge workers the power of generative AI and agentic workflows and leveraging data sources from across your organization. Google Agentspace includes prebuilt connectors for the most commonly-used third-party applications — such as Confluence, Jira, Microsoft SharePoint, and ServiceNow — giving employees a single multimodal search interface with permissions-aware access to enterprise information. Agentspace can provide conversational assistance, answer complex questions, and host custom AI agents that apply generative AI contextually.

Google Agentspace home screen.

Use cases for Agentspace

You can use Agentspace to answer questions, carry out tasks, and iterate on deliverables based on connected data sources from across your organization. You can use Agentspace in the following ways:

Use case Example prompts
Create images, videos, and reports Create a series of three images for a social media campaign promoting our new line of artisanal coffee beans.
I'm attaching the latest company 10-K report. Analyze it and give me a summary of the key financial highlights and risk factors.
Turn the attached blog post about our company's history into a short documentary-style video, using archival photos and a professional voiceover.
Handle administrative tasks I have a late fee in my expense report; what do I do to resolve it?
Help me book a conference room for my team meeting next Tuesday from 10 to 11 AM.
Research, ideate, and plan Summarize our best-performing campaigns from last year and give me three new ideas for our upcoming holiday promotion.
My customer is Cymbal Insurance and I'm meeting with their Head of Procurement on Thursday. Find their latest earnings report and give me a list of talking points.
We are considering consolidating our shipping with a single logistics provider. Can you research the pros and cons of a "single-provider" strategy, and then identify the top three logistics partners for a company of our size?
Learn about people and projects Find all the documentation related to our Go-To-Market strategy for the new product line.
Who is Hao S. and what projects are they currently working on?

Why use Agentspace?

Agentspace connects the content across your organization and uses it to generate grounded and personalized answers using Google's premier knowledge discovery tools.

With Agentspace, you can:

  • Ingest large volumes of enterprise data from multiple formats and platforms into a single app.
  • Sync and search across data from SaaS systems such as Salesforce, Jira, Confluence, and more.
  • Enforce access-controlled search results and generative answers at scale.
  • Streamline agentic workflows and eliminate the need to switch between multiple AI assistance and agent applications.
  • Create and configure AI assistants offering generative answers from enterprise or public data.
  • Use out-of-the-box agents, available to you in the Agents gallery.
  • Assemble your own no-code agent with Agent Designer.

Agentspace offers an array of unique advantages for enterprises:

  • Built-in trust through SSO and user-level access.
  • Google intelligence that learns from user behavior and ancipates the next question.
  • Broad connectivity across cloud platforms, CRMs, productivity tools, and legacy systems.
  • Enterprise-wide customization with user-specific personalization.
  • Real-time feedback and adaptation that continuously improves results.
  • Customizable RAG agent grounded on enterprise data from a wide variety of supported formats.
  • Scalability across geographies and languages.

NotebookLM Enterprise, AI-powered research and knowledge assistant

Included with Google Agentspace, NotebookLM Enterprise is an AI-powered research and knowledge assistant that helps you to summarize information, brainstorm ideas, and write with confidence. You may use NotebookLM Enterprise to create notebooks that contain your notes, sources, and ideas.

Next steps

For more information about Google Agentspace, see the following pages.