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.

Note: This is the second course in the 'Generative AI Engineering with Databricks’ series. It was previously named 'Generative AI Application Development'.

Skill Level

Associate

Duration

Prerequisites

The content was developed for participants with these skills/knowledge/abilities:

• Python-Specific Prerequisites

Learners must be comfortable writing production-quality Python, not scripts.

- Core Python syntax and data structures

- Functions, classes, and basic OOP patterns

- Exception handling and error propagation

- Decorators

- Type hints and docstrings

• SQL-Specific Prerequisites

Learners must be able to define reusable SQL logic, not just query tables.

- Writing SELECT queries with filters and aggregations

- Understanding SQL data types and NULL handling

- Creating parameterized SQL functions

- Using CREATE OR REPLACE FUNCTION syntax

- Writing clear SQL comments for documentation

• Databricks-Specific Prerequisites

Learners must be comfortable operating inside the Databricks platform.

- Navigating the Databricks workspace and notebooks

- Running notebook cells and interpreting outputs

- Understanding basic compute concepts (especially serverless)

- Using Catalog Explorer to inspect registered assets

- Awareness of Databricks-managed services (Model Serving, AI Playground)

• GenAI / Agent-Specific Prerequisites

Learners must understand how LLM-powered agents behave, even if frameworks are taught in-course.

- What Large Language Models are and what they can and cannot do

- Basic prompt engineering concepts

- High-level understanding of Retrieval-Augmented Generation (RAG)

- Conceptual understanding of agent reasoning and tool invocation

- Familiarity with REST APIs and JSON payloads

• Optional but Helpful (Not Required)

- MLflow fundamentals (tracking, model registry, tracing)

- Agent frameworks (e.g., LangChain)

• Databricks-related recommended training: AI Agents Fundamentals, Get Started with AI Agents

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Customer registration Partner registration

See all our registration options

Registration options

Databricks has a delivery method for wherever you are on your learning journey

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Instructor-Led

Public and private courses taught by expert instructors across half-day to two-day courses

Blended Learning

Self-paced and weekly instructor-led sessions for every style of learner to optimize course completion and knowledge retention. Go to Subscriptions Catalog tab to purchase

Purchase now

Skills@Scale

Comprehensive training offering for large scale customers that includes learning elements for every style of learning. Inquire with your account executive for details

Upcoming Public Classes

Model Development at Scale

In this course, you will develop an in-depth understanding of how to design, implement, and govern scalable machine learning systems that operate effectively at enterprise scale. The curriculum is organized into three experiential modules: developing distributed ML workflows with frameworks such as Apache SparkML and Ray, transitioning local ML development to distributed compute using tools like Pandas on Spark, and operationalizing and governing production models with Databricks’ MLOps ecosystem.

Through hands-on projects, you will construct end-to-end distributed ML pipelines using the SparkML workflow, applying Transformers, Estimators, and the fit/transform paradigm for both classification and regression tasks. You will version, compare, and manage experiments using MLflow 3.0 to ensure reproducibility and governance, capturing lineage between data, features, and model artifacts. Additionally, you will apply scalable Hyperparameter Optimization frameworks to improve model performance at scale.

The course concludes by demonstrating complete lifecycle management, from experimentation to production deployment, using Unity Catalog and Model Serving. You will learn to operationalize trained models, monitor their performance, and implement strong governance over models, features, and Delta assets within the Databricks environment.

Paid & Subscription

Lab

Professional

Data Warehousing Practitioner

Delivery Specialization: EDW Migration Best Practices

This course is meant to provide guidance on best practices for executing a successful migration from Enterprise Data Warehouses (EDWs) - e.g. Netezza, Teradata, Oracle, and Microsoft SQL Server - to Databricks. It covers a wide range of migration processes starting from initial discovery all the way through to delivery.

Note: Databricks Academy is transitioning from video lectures to a more streamlined PDF format with slides and notes for all self-paced courses. Please note that demo videos will still be available in their original format. We would love to hear your thoughts on this change, so please share your feedback through the course survey at the end. Thank you for being a part of our learning community!

Data Warehousing Practitioner

Delivery Specialization: CDW Migration Best Practices

This course is meant to provide guidance on best practices for executing a successful migration from Cloud Data Warehouses (CDWs) - e.g. Amazon Redshift, Snowflake, and Synapse Analytics - to Databricks. It covers a wide range of migration processes starting from initial discovery all the way through to delivery.