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 Looker-hosted. We recommend that customers who participate in the Looker 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. Optionally, an admin can enable the Code Interpreter to access advanced analytics. The Trusted Tester capabilities must be enabled to use the Code Interpreter.

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.

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