Conversational Analytics: Data agents

Introduction

Data agents build on the power of Conversational Analytics to further refine the experience of users who, with no expertise in business intelligence, need to gain value from your data. With data agents, you can customize the AI-powered data-querying agent with context and instructions that are specific to your data.

For example, maybe you define a "loyal" customer as one who has made more than five purchases within a certain timeframe. Or, because you want to save your users time, all responses from your data agent should be summarized in 20 words or fewer. Also, you want numbers to be formatted to match company standards. These types of instructions and more can be used to build a data agent that knows how your users want to interact with your data.

This page guides you through the following processes:

Learn how and when Gemini for Google Cloud uses your data. As an early-stage technology, Gemini for Google Cloud products can generate output that seems plausible but is factually incorrect. We recommend that you validate all output from Gemini for Google Cloud products before you use it. For more information, see Gemini for Google Cloud and responsible AI.

Before you begin

To use Conversational Analytics in Looker Studio, you must meet the following requirements.

  1. You must be a user under a Looker Studio Pro subscription. Looker Studio Pro licenses are available at no cost to Looker users.
  2. An administrator must have enabled Gemini in Looker for Looker Studio.

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

  1. A Looker admin must enable Gemini in Looker for the Looker instance.
  2. A Looker admin must grant you the Gemini role in the Looker instance. You must also have a role that contains the access_data permission for the model that you are querying.

Known limitations

Because data agents are a part of Conversational Analytics, they are also subject to the same limitations as Conversational Analytics. For more information, see this discussion about the limitations of Conversational Analytics.

Creating and managing data agents

You can create new data agents to connect to Looker Studio data sources for which you have the Viewer role. Agents can be managed in the Manage agents tab of the left navigation panel. When you're creating or editing a data agent, you have the ability to test your settings before confirming them.

Creating a new data agent

To create a new data agent, follow these steps:

  1. Navigate to Conversational Analytics within Looker Studio or within Looker.
  2. Select + Create agent in the Chat with your data section. Or, in the left navigation panel, select Manage agents, and then select + Create agent.

  3. On the New agent page, provide the following information about your data agent. Once you provide these details, you can't change the data source that is associated with the agent, but you can edit the agent's name, description, and instructions at any time.

    • Agent Name: Enter a name for the agent. The name should be unique and descriptive.
    • Description: Briefly describe what this agent can do and the data that it uses. Users will see this description when they select the agent to start a conversation or when you share the agent with them, so make sure it clearly explains the agent's purpose and how it can be helpful.

    • Data: Select the existing Looker Studio data source that you want to connect to, or select Connect to data in the Select data for agent window to create a new data source. To select an existing data source, follow these steps:

      1. In the Data field, click Select data.
      2. In the Select data from Agent window, under Name, click the name of a data source.
      3. Click Select to add the selected data source to the data agent.

  4. Instructions: Provide context to help Conversational Analytics understand how to interact with your data and provide accurate and relevant responses. For examples of the types of context that you can provide, see Writing agent instructions.

  5. To save your new data agent, click Save.

After you save the data agent, you can share the agent with other users and start a conversation with the agent.

Writing agent instructions

When you create a data agent, you can provide the following types of context in the Instructions field:

  • Synonyms: Alternative terms for key fields
  • Key fields: The most important fields for analysis
  • Excluded fields: Fields that the data agent should avoid
  • Filtering and grouping: Fields that the agent should use to filter and group data

Here are some sample instructions to adjust and test with your agent:

  • Unless stated otherwise, always filter the data on Order Items Created Year = 2024
  • We consider "loyal" customers to be those with Order Items Count > 5
  • If someone says anything about "Location," that means User City
  • If the question mentions "Seniors", those are users with User Age > 65
  • If a question is about Revenue, use Total Sales
  • When someone says "by product", unless they specifically say "name", group by product category
  • "Successful" orders means that Order Items status = "Complete"
  • Whenever there is a question of a timeline, or over time, always use Order Item Created Date as the field to group by

Testing an agent

When you're creating or editing an agent, the agent details page includes the Preview your agent pane. You can test agent settings and instructions by starting a conversation with the agent.

Editing an existing data agent

To edit an existing data agent, follow these steps:

  1. Navigate to Conversational Analytics within Looker Studio or within Looker.
  2. In the left navigation panel, click Manage agents.
  3. On the Manage agents page, select the data agent that you want to edit.

  4. Update the details about the agent as needed. You can modify the details that you specified when you created the agent, including the Agent Name, Description, and Instructions fields.

  5. To save your changes, click Save.

Deleting a data agent

To delete a data agent, follow these steps:

  1. Navigate to Conversational Analytics within Looker Studio or within Looker.
  2. In the left navigation panel, click Manage agents.
  3. On the Manage agents page, hold your cursor over the data agent that you want to delete.
  4. Click More options .
  5. Select Delete.
  6. In the Move to trash window, click Move to trash to delete the data agent.

Agents that are moved to the trash will be permanently deleted after 30 days. You can permanently delete a data agent manually, or you can restore a data agent from the trash before it is permanently deleted.

Permanently deleting a data agent

To permanently delete a data agent, follow these steps:

  1. Navigate to Conversational Analytics.
  2. In the left navigation panel, expand the Trash section.
  3. Select the data agent that you want to delete.
  4. In the Are you sure? window, click Delete forever.

Restoring a data agent from the trash

To restore a data agent from the trash, follow these steps:

  1. Navigate to Conversational Analytics.
  2. In the left navigation panel, expand the Trash section.
  3. Select the data agent that you want to restore.
  4. In the Are you sure? window, click Restore.

Starting a conversation with an agent

You can start a conversation with a data agent that you created or that another user has shared with you. To start a conversation with an agent, follow these steps:

  1. Navigate to Conversational Analytics within Looker Studio or within Looker.
  2. In the left navigation panel, click + Create conversation.
  3. On the Chat with your data page, in the Agents tab, select the agent that you want to start a conversation with.
  4. Type in your question and press return (Mac) or Enter (PC) to start the conversation.

You can return to the conversation from the Recent section.

Sharing data agents

Only the owner of a data agent can share an agent. The recipients of a shared data agent can see the agent's description but cannot edit the agent. Once an agent is created, it may take a few minutes for it to become shareable.

How to share a data agent

To share a data agent, follow these steps:

  1. Navigate to the Manage agents page.
  2. Hold your cursor over the data agent and select Share data agent, or select Share while editing an existing data agent.
  3. You can invite specific people or Google Groups to share the agent. You can also share more broadly by turning on link sharing for a report.
  4. Once you have added the individuals or groups to the People with Access section, click Done.

The recipient will receive an email with a link to the data agent. When a user selects Create conversation, agents that have been shared with them will appear under Agents. After an agent is initially shared, users won't be able to view the instructions for that agent. Include any relevant information in the agent description.

Revoking access to a data agent

To revoke access to an agent, remove the person or group from the list of People with access in the Share menu of the agent. If the removed user has an ongoing conversation, they will still have access for a minute or two while the changes propagate.

If a user tries to ask more questions once access to an agent is removed, they will see the message The agent in this conversation may not be shared with you, or may have been deleted. You can view any past conversations with the agent, but can't ask new questions.