# KodeKloud: Courses AI Agents For Data Analytics ## AI Agents For Data Analytics ### Building Agent With BigQuery - [Course: AI Agents For Data Analytics](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/index.md): Course teaching how to build AI agents that use the MCP Toolbox to generate and execute SQL across BigQuery, Snowflake, and Databricks for real data analytics. - [Welcome to Bluepine](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Welcome-to-Bluepine/page.md): Course teaching how to build AI agents that use the MCP Toolbox to generate and execute SQL across BigQuery, Snowflake, and Databricks for real data analytics. - [What Are We building](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/What-Are-We-building/page.md): Designing an agent that uses a reasoning model, plain instructions, and discoverable tools to fetch and join customer data across BigQuery Databricks and Snowflake to assess churn risk - [Course Prerequisites](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Course-Prerequisites/page.md): Prerequisites and setup guidance for a course covering Python, Google ADK, and basic SQL with recommended development environment, tools, and resource links. - [Building a Simple Churn Agent](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Building-a-Simple-Churn-Agent/page.md): Guide to building a minimal LLM agent that uses a simple lookup tool and two fake customer records to identify churn risk and recommend retention actions - [Integrating Agent With BigQuery](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Integrating-Agent-With-BigQuery/page.md): Explains integrating a conversational agent with BigQuery using parameterized SQL, a narrow get_customer tool, credentials, schema and guidance to assess customer churn from real feature tables. - [Why MCP Matters](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Why-MCP-Matters/page.md): Explains how MCP servers let AI agents generate SQL and centralize data integrations to reduce developer overhead and speed queries while emphasizing security and governance - [Meet MCP Toolbox](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Meet-MCP-Toolbox/page.md): Introducing Google's MCP Toolbox for Databases and how agents use it with ADK to run BigQuery tools like schema inspection and SQL execution to automate analytics queries - [Integrating BigQuery via MCP Toolbox](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Integrating-BigQuery-via-MCP-Toolbox/page.md): Shows how to integrate BigQuery with an LLM agent using the MCP Toolbox to run SQL, inspect schema, and perform churn analysis with filtered tools. - [Demo Building Google ADK Agent With BigQuery MCP](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-BigQuery/Demo-Building-Google-ADK-Agent-With-BigQuery-MCP/page.md): Tutorial to build a Google ADK churn detection agent using the MCP Toolbox to query BigQuery and produce model-driven customer risk assessments ### Building Agent With Databricks - [Tradeoffs of Function Tools and MCP](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Databricks/Tradeoffs-of-Function-Tools-and-MCP/page.md): Comparison of function tools versus MCP for querying production BigQuery, weighing safety, auditability, flexibility, setup complexity, and reuse to guide deployment choices. - [Govern at Credentials Not the Prompt](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Databricks/Govern-at-Credentials-Not-the-Prompt/page.md): Advocates governing agent credentials with least privilege using dedicated service accounts and read-only roles instead of prompt-based guards, plus guidance on function tools versus MCP read toolsets - [Introduction to Databricks Genie Space](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Databricks/Introduction-to-Databricks-Genie-Space/page.md): Describes Databricks Genie Space, a natural language to SQL semantic layer that maps curated table metadata into executable queries and enforces credential based governance for agents. - [Demo Building Agent With Databricks](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Databricks/Demo-Building-Agent-With-Databricks/page.md): Guide to building a Databricks-based churn detection LLM agent using MCP streamable HTTP, including environment setup, Python example, transport options, and sample assessment output ### Building Agent With Snowflake - [Integrating Agent With Snowflake MCP](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Snowflake/Integrating-Agent-With-Snowflake-MCP/page.md): Explaining how to integrate a read-only Snowflake connector into an agent via MCP toolbox, enforcing least-privilege access for safe billing data queries. - [One Agent and Three Data Layers](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Snowflake/One-Agent-and-Three-Data-Layers/page.md): Demonstrates using one LLM agent with prebuilt connectors to query Snowflake, BigQuery, and Databricks to combine billing, usage, and support data for customer prioritization - [Demo Integrating Google ADK Agent With Snowflake MCP](https://notes.kodekloud.com/docs/AI-Agents-For-Data-Analytics/Building-Agent-With-Snowflake/Demo-Integrating-Google-ADK-Agent-With-Snowflake-MCP/page.md): Guide to adapting a Google ADK churn-detection LLM agent to use Snowflake via the MCP Toolbox, including environment setup and toolbox adapter configuration