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](https://codelabs.developers.google.com/ca-api-bigquery) | 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](https://codelabs.developers.google.com/codelabs/looker-ca-api) | 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](https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/agents/gemini_data_analytics/intro_gemini_data_analytics_http.ipynb) | 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](https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/agents/gemini_data_analytics/intro_gemini_data_analytics_sdk.ipynb) | 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](https://cloud.google.com/blog/products/data-analytics/build-data-agents-with-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:

- [Streamlit Quickstart app](https://github.com/looker-open-source/ca-api-quickstarts): Learn how to integrate with the Conversational Analytics API in a local test environment.
- [Conversational Analytics demos and tools](https://github.com/looker-open-source/ca-demos-and-tools): Review demos and tools that showcase Conversational Analytics API capabilities and provide practical integration patterns.
- [YouTube: Conversational Analytics API](https://www.youtube.com/watch?v=c3WSg0Bpmt4): Learn about the Conversational Analytics API, including how the API processes natural language questions, connects to data sources such as BigQuery and Looker, and returns results as text or visualizations.
- [YouTube: Embed analytics experiences in your applications using the Conversational Analytics API](https://www.youtube.com/watch?v=p-MguQf84Tg): Learn about the Conversational Analytics API and how to build a Conversational Analytics API agent by using the Agent Development Kit (ADK).

## 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:

- [.NET (v1beta)](https://docs.cloud.google.com/dotnet/docs/reference/Google.Cloud.GeminiDataAnalytics.V1Beta/latest.md.txt)
- [Go (v1beta)](https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/geminidataanalytics/latest/apiv1beta.md.txt)
- [Node.js](https://www.npmjs.com/package/@google-cloud/geminidataanalytics)
- [PHP (v1beta)](https://docs.cloud.google.com/php/docs/reference/cloud-geminidataanalytics/latest.md.txt)
- [Python (v1beta)](https://docs.cloud.google.com/python/docs/reference/google-cloud-geminidataanalytics/latest.md.txt)
- [Ruby (v1beta)](https://docs.cloud.google.com/ruby/docs/reference/google-cloud-gemini_data_analytics-v1beta/latest.md.txt)
- [Java](https://docs.cloud.google.com/java/docs/reference/google-cloud-geminidataanalytics/latest/overview.md.txt)

### Agent Development Kit (ADK)

The [Agent Development Kit (ADK)](https://adk.dev/) includes tools for building and managing Conversational Analytics API data agents:

- [`ask_data_agent`](https://adk.dev/integrations/data-agent/): Ask natural language questions of a pre-configured data agent by referencing the agent's ID.
- [`ask_data_insights`](https://adk.dev/integrations/bigquery/): 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](https://mcp-toolbox.dev/documentation/introduction/) 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 that enable interaction with services such as BigQuery and Looker.

The toolbox includes MCP-compatible tools for the following services:

- [BigQuery Conversational Analytics tool](https://mcp-toolbox.dev/integrations/bigquery/tools/bigquery-conversational-analytics/) (`bigquery-conversational-analytics`)
- [Looker Conversational Analytics tool](https://mcp-toolbox.dev/integrations/looker/tools/looker-conversational-analytics/) (`looker-conversational-analytics`)

### Other development tools

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

- [Prism](https://github.com/looker-open-source/ca-demos-and-tools/blob/main/ca-agent-ops-prism/README.md): Use this open-source application to monitor and evaluate AI agent performance, run test suites, and capture traces.