Set up Conversational Analytics in Looker

This page guides you through setting up Conversational Analytics in Looker, including setup requirements, required permissions to use Conversational Analytics, and supported data sources.

Learn how and when Gemini for Google Cloud uses your data.

Before you begin

To use Conversational Analytics within a Looker instance, you and your Looker instance must meet the following requirements:

  1. Gemini in Looker must be enabled for the Looker instance.
    • To access these features in a Looker (original) instance, a Looker admin must enable Gemini in Looker in the Looker (original) instance settings. The instance must be on Looker 25.2 or later and be Looker hosted. We recommend that customers participating in Lookers Extended support release program update to Looker 25.6 or later to use Conversational Analytics. To use Conversational Analytics data agents, update your instance to Looker 25.18.9 or later.
    • To access these features in a Looker (Google Cloud core) instance, a user with the Looker Admin (roles/looker.admin) IAM role must enable Gemini in Looker in the Looker (Google Cloud core) instance settings in the Google Cloud console.
  2. The Trusted Tester capabilities must be enabled to use Conversational Analytics during the Preview period.
  3. Optionally, an admin can enable the Code Interpreter to access advanced analytics.

Required Looker permissions

To use Conversational Analytics in Looker, a Looker admin must grant you a Looker role that contains the gemini_in_looker permission for the models that you're querying. This permission is available as part of the default Gemini role. You must also have a role that contains the access_data permission for the model that you are querying.

The use of a data agent is managed through a combination of content access, data access, and feature access. To perform the tasks that are described in the following table, you must be assigned a Looker role that has the required permissions for the models that your data agent will query and, in some cases, access to the agent itself.

Task Required Looker permissions Required level of data agent access
Create, edit, share, and delete agents Added 25.18 admin_agents No content access must be granted
Create, edit, share, and delete agents Added 25.18 save_agents Manage access; Edit (this access is granted automatically if the user creates the agent; otherwise, Manage access; Edit access must be granted by the agent's creator by sharing the agent)
Chat with a data agent from the Agents tab in Conversational Analytics access_data (on each model that contains the Explores that are used by the data agent)

Added 25.18 chat_with_agent		 View access
Chat with a Looker Explore from the Explores tab in Conversational Analytics access_data (on each model that contains the Explores that are used by the data agent)

Added 25.18 chat_with_explore

Looker also has the following default roles that contain subsets of these permissions for all models on the instance:

  • Conversational Analytics Agent Manager: With this role, a user can create, edit, share, delete, and chat with agents that they have Manage access; Edit access for and chat with Explores
  • Conversational Analytics User: With this role, a user can chat with an agent that they have View access for
  • Admin: By default, this role (Looker Admin) has all permissions and content access across the instance.

A Looker admin can grant these roles and permissions on the Roles page in the Admin section of the Looker instance. For more information about Looker roles, see the Admin settings – Roles documentation page.

The creator of the data agent can manage individual users' access to the agent by sharing the agent.

Supported data sources

You can converse with the following data sources through the Conversational Analytics interface:

When you "chat" with an Explore, you're essentially having a conversation with a specific, predefined dataset. This is a direct way to ask questions about the data within that Explore. You can have a conversation with up to five Explores.

Data agents are AI-powered assistants that you can create and customize. You can give them specific instructions and connect them to your Looker Explore data.

For strategies and best practices to help Looker admins and LookML developers successfully configure, deploy, and optimize Conversational Analytics, including LookML best practices for Conversational Analytics, tips on when to add context to LookML versus Conversational Analytics, and best practices for setting up an Explore for use with Conversational Analytics, see the Best practices for configuring Conversational Analytics in Looker documentation page.

What's next