Conversational analytics in BigQuery

Conversational analytics in BigQuery lets you chat with your data using conversational language. Using conversational analytics, you can create data agents to define context and query processing instructions for a set of data sources. The context and instructions configure the data agents to effectively answer questions for specific use cases. Users can then have conversations with data agents to ask questions about BigQuery data using natural language. Users can also create direct conversations with one or more tables to answer quick, one-off questions.

Conversational analytics is powered by Gemini for Cloud de Confiance by S3NS.

Learn how and when Gemini for Cloud de Confiance uses your data.

Data agents

Data agents consist of one or more data sources, and a set of use case-specific instructions for processing that data. When you create a data agent, you can configure it by using the following options:

  • Provide table metadata to describe the data in the most appropriate way for the given use case.

  • Provide instructions for interpreting and querying the data, such as defining the following:

    • Synonyms for field names
    • Most important fields
    • Defaults for filtering and grouping

  • Create golden queries that the data agent can use to learn the business logic used by your organization.

Data agents that you create in BigQuery are accessible by other services in the project that support data agents, such as the Conversational Analytics API and Looker Studio.

You can create and manage data agents in BigQuery by using the Cloud de Confiance console. For more information, see Create data agents.

Conversations

Conversations are persisted user chats with a data agent or data source. Users can ask data agents multi-part questions that use common terms like "sales" or "most popular", without having to specify table field names or define conditions to filter the data. The chat response returned to the user provides the answer to the user's question as text and code, and also generates charts where appropriate. The response also includes the reasoning behind the results.

When you create a direct conversation with a data source, the Conversational Analytics API interprets your question without the context and processing instructions offered by a data agent. Because of this, direct conversation results can be less accurate. Use data agents in cases where greater accuracy is required.

You can create and manage conversations in BigQuery by using the Cloud de Confiance console. For more information, see Create conversations.

Security

You can manage user access to conversational analytics in BigQuery by using Conversational Analytics API IAM roles and permissions. For information about the roles needed for specific operations, refer to the data agent required roles and the conversation required roles.

Locations

Conversational analytics operates globally, you can't choose which region to use.

Pricing

You are charged at BigQuery compute pricing for queries that are run when you create data agents and have conversations with data agents or data sources. There is no additional charge for creating and using data agents and conversations during the early access period.

What's next