Conversational Analytics API tutorials, demos, and tools

To help you build and evaluate data agents with the Conversational Analytics API, this page provides links to guided tutorials, interactive demos, sample applications, and development tools.

Interactive tutorials

This section links to codelabs, interactive Colaboratory notebooks, and blog posts that provide step-by-step guidance to help you learn core API concepts.

Resource Description Format
Introduction to the Conversational Analytics API Follow a step-by-step tutorial to learn how to use the Python SDK with a BigQuery data source, how to create a new agent by using the Conversational Analytics API, how to create and manage conversations, and how to send and stream responses from the API. Codelab
Build a chat app with the Conversational Analytics API for Looker and BigQuery Learn how to use the Conversational Analytics API with Looker and BigQuery to build a chat application, including how to set up the Streamlit Quickstart app, and learn about the benefits of Looker for semantic modeling. Codelab
HTTP Colaboratory notebook Explore an interactive, step-by-step guide to setting up your environment, building a data agent, and making API calls by using HTTP requests. Notebook
Python SDK Colaboratory notebook Explore an interactive, step-by-step guide to setting up your environment, building a data agent, and making API calls by using the Python SDK. Notebook
Blog: Building a conversational agent in BigQuery using the Conversational Analytics API Learn to build a BigQuery conversational agent by using the Python SDK, with guidance on setup, stateful conversations, and streaming responses. Blog

Sample applications and demos

This section links to sample applications and video demonstrations that showcase the API's capabilities.

Sample apps and videos

The following resources demonstrate how to integrate the Conversational Analytics API in various environments and provide overviews of API features:

SDKs and development tools

This section provides links to client libraries, the Agent Development Kit (ADK), the MCP Toolbox, and other tools for building, managing, and evaluating data agents.

Client libraries

Installation instructions and reference documentation are available for the following Conversational Analytics API client libraries:

Agent Development Kit (ADK)

The Agent Development Kit (ADK) includes tools for building and managing Conversational Analytics API data agents:

  • ask_data_agent: Ask natural language questions of a pre-configured data agent by referencing the agent's ID.
  • ask_data_insights: Generate natural language data insights from sources such as BigQuery with a stateless API call that doesn't require a data agent.

MCP Toolbox for Databases

The MCP Toolbox for Databases is an open-source MCP server that connects AI agents, IDEs, and applications to data sources. It wraps the Conversational Analytics API as MCP-compatible tools, enabling interaction with services such as BigQuery and Looker.

To learn how to use the MCP Toolbox with specific services, see the following guides:

Other development tools

The following tool can assist with other development tasks, such as agent evaluation:

  • Prism: Use this open-source application to monitor and evaluate AI agent performance, run test suites, and capture traces.