Generative AI Engineering with Databricks

This course is aimed at data scientists, machine learning engineers, and other data practitioners who want to build generative AI applications using the latest and most popular frameworks and Databricks capabilities. 

Note: Databricks Academy is transitioning to a notebook-based format for classroom sessions within the Databricks environment, discontinuing the use of slide decks for lectures in the first three modules. You can access the lecture notebooks in the Vocareum lab environment.

Below, we describe each of the four, four-hour modules included in this course.

Building Retrieval Agents On Databricks: This course provides hands-on training for building retrieval agents on the Databricks Data Intelligence Platform. Participants will learn to parse unstructured documents into structured data, transform and chunk content for retrieval workflows, build vector search solutions for document retrieval, and develop production-ready agents using MLflow and Agent Bricks. The course covers the complete agent lifecycle from document processing through embedding generation, vector indexing, and agent deployment with governance capabilities.

Building Single-Agent Applications on Databricks: This course provides hands-on training for building single-agent applications on the Databricks Data Intelligence Platform. Students will learn to create AI agents that leverage Unity Catalog functions as tools, implement comprehensive tracing and monitoring with MLflow, and deploy agents using both traditional frameworks like LangChain and modern solutions like Agent Bricks. The course covers the complete agent lifecycle from initial tool creation and testing in AI Playground through production deployment with governance, evaluation, and continuous improvement capabilities.

Agent Evaluation on Databricks: This course teaches students how to systematically evaluate AI agents using MLflow's evaluation framework, addressing the unique challenges of non-deterministic AI systems that traditional software testing cannot handle. Students learn to implement various evaluation approaches including built-in judges for common criteria like correctness and safety, guideline judges for business-specific requirements, and custom judges for specialized needs. The course covers both offline evaluation using curated datasets and online production monitoring, with hands-on experience using MLflow's tracing capabilities to understand agent execution patterns and collect human feedback from different stakeholder types. Through practical demonstrations and labs, students develop skills in creating evaluation workflows that drive continuous quality improvements throughout the AI agent development lifecycle.

Generative AI Application Deployment and Monitoring: Ready to learn how to deploy, operationalize, and monitor generative deploying, operationalizing, and monitoring generative AI applications? This module will help you gain skills in the deployment of generative AI applications using tools like Model Serving. We’ll also cover how to operationalize generative AI applications following best practices and recommended architectures. Finally, we’ll discuss the idea of monitoring generative AI applications and their components using Lakehouse Monitoring.