This page describes the concepts related to Agentspace and gives you a quick overview of configuring and using Agentspace.
Agentspace concepts
Agentspace is composed of several key concepts that work together to provide a powerful search and action platform. These concepts include data sources, data stores, apps, assistants, actions, agents, and analytics.
| Concept | Description |
|---|---|
Data sources |
You can connect Google and third-party data sources to Google Agentspace and store the data in dedicated data stores. To connect your data sources, see Connect a Google data source and Connect a third-party data source. |
Data stores |
Each data source supports a set of entity types. For example, Jira Cloud has entities such as issues, attachments, comments, and worklogs, which are unique to the data source. Agentspace creates a separate data store for each entity. Therefore, when you create a data store using the Google Cloud console, you get a collection of data stores representing these ingested data entities.To learn about Google Agentspace data stores, see Introduction to connectors and data stores. |
Apps |
An Agentspace app provides
search results, actions, and agents to your end users. The term app
can be used interchangeably with the term engine in the context of
APIs. An app must be connected to a data store in order to use the data
from it to serve search results, answers, or actions.
Apps have a many-to-many relationship with data stores. When multiple data stores are connected to a single app, this is referred to as blended search. For information about connecting a search app to more than one data store, see About blended search. To learn more about creating an app, see Create an app. |
Assistant |
The in-app chat box, known as the assistant, is grounded with the
content in the data stores and adheres to the defined security, privacy,
and compliance safeguards.
The assistant generates answers to queries and answers follow-up questions, ground answers in your enterprise data with citations and provide optional grounding and citations based on external public website data, analyze and summarize content such as PDFs and images that you upload, and answer follow-up questions about it, and generate images based on text prompts and create reports with streamed research during the creation process. To learn about using the assistant, see Use the assistant. |
Actions |
Assistant actions allow the assistant to perform tasks on behalf of users.
For example, if your app connects to Google calendar and Jira Cloud data
sources, users can instruct the assistant to create Google Calendar events
or edit Jira Cloud issues.
You can turn on assistant actions for the following data stores:
|
Agents |
The Agents gallery is a portal in Agentspace that lets you access, create, and manage agents. It showcases agents premade by Google (such as Deep Research), agents that your organization has created or added, and agents that you create using Agent Designer. For more information, see Browse agents with Agents gallery. |
Analytics |
Analytics give you insight into the usage trends, search quality, and end-user engagement of your app. The console provides an interactive dashboard experience powered by Looker. For more information, see View and export analytics data. |