Databricks Get Started Days (Lakebase + AI Agents)

Get Started with Lakebase

This get started course introduces Databricks Lakebase, a fully managed PostgreSQL service built into the Databricks Data Intelligence Platform that brings operational (OLTP) and analytical (OLAP) workloads closer together.

The course begins with a conceptual lecture that compares OLTP and OLAP systems, explaining their different performance characteristics, storage models, and typical use cases. You will also explore the challenges organizations face when maintaining separate transactional databases and analytical platforms, including data movement, latency, and architectural complexity.

You will then learn how Databricks Lakebase helps address these challenges by providing a PostgreSQL-compatible operational database that integrates directly with the Databricks Lakehouse, enabling operational applications and analytics to work together within a unified platform.

This is a Get Started course, so the focus is on understanding the core concepts and basic workflows for working with Lakebase. Building full production applications on top of Lakebase is outside the scope of this course.

By the end of the course, you will understand how Lakebase enables organizations to bridge operational systems and analytics within a single governed platform powered by Unity Catalog and the Databricks Lakehouse.

Get Started with AI Agents on Databricks

This course is an introduction to AI agents, their role in modern AI applications, and how to build AI agent applications on the Databricks platform. You'll learn about the principles of AI agents, how they differ from traditional AI systems, and explore their key components. Through interactive demos and hands-on labs, you'll see how to build, deploy, and evaluate AI agents on Databricks using Databricks AI and Agent Bricks. By the end of this course, you'll understand how to create and deploy AI agents using the Databricks Data + AI Platform.

You can create a Databricks Free Edition account and try the follow-along demos in a hands-on environment.

Skill Level

Onboarding

Duration

Prerequisites

Get Started with Lakebase

• Access to a Databricks workspace with the Lakebase Database feature enabled

• An available All-purpose-compute OR Serverless cluster and a SQL Warehouse (2X-Small is sufficient).

• Create permissions for catalogs in your workspace.

• Intermediate SQL skills - Able to write and understand SELECT, INSERT, UPDATE, and DELETE statements.

• Intermediate Python knowledge - Comfortable with Python functions, exceptions, and working with dictionaries/lists.

• Familiarity with OLTP fundamentals - Understands client-server relationships, ACID properties, database authentication, and concurrent access.

Get Started with AI Agents on Databricks

• Navigating the Databricks workspace, including accessing the left navigation menu and using the UI for locating AI/ML features.

• Awareness of Unity Catalog as the governance and data management layer within Databricks.

• Basic experience with Databricks UI workflows (e.g., configuring resources, accessing deployed endpoints).

• Ability to run provided code snippets (e.g., Python, SQL, or curl) to query the agent endpoint, if integrating programmatically.

• Basic familiarity with copying and pasting code examples from the UI and modifying simple parameters (such as endpoint names).

• Light SQL-authoring experience.

• No advanced programming is required, but users should be comfortable following instructions to interact with APIs or endpoints if needed.

Outline

1. Get Started with Lakebase

• Lakebase Core Concepts and Architecture

• Demo: Creating and Exploring a Lakebase Project

• Demo: Querying Lakebase with Lakehouse Federation

• Demo: Syncing Unity Catalog Tables to Lakebase Postgres Tables

• Demo: Lakebase Autoscaling and Python CRUD Quickstart

• Bonus Lab: Building Your First Databricks App with Lakebase Autoscaling

2. Get Started with AI Agents on Databricks

Introduction to AI Agents

• What is an AI Agent?

• AI Agent Patterns

• AI Agent Components

• Common Agentic AI Use-Cases

Building AI Agents on Databricks

• The Challenges with Agents in Production

• Overview of Agent Development

• Custom Agent Development

• Demo: Get Started with AI Agents on Databricks

• Demo: Build Agent Tools and Prototype with AI Playground

Agent Evaluation and Deployment

• Agent Evaluation and MLflow

• Demo: From AI Playground to Deployment

• Lab: Creating Tools and Testing in the Playground

• Deploying Agents & Model Serving

Production-Ready Agents with Agent Bricks

• Introduction to Agent Bricks

• Lab: Build a Knowledge Assistant with Agent Bricks

Public Class Registration

If your company has purchased success credits or has a learning subscription, please fill out the Training Request form. Otherwise, you can register below.

Customer registration Partner registration

Private Class Request

If your company is interested in private training, please submit a request.

Request Private Training

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

Preparing for Databricks Certification Exams

Welcome to this course on preparing for your Databricks Certification exam. While most of the information found within this course is available on the Databricks Certification website, this training seeks to summarize that content to simplify your preparation.

Please note that this course will not teach any of the content on any particular exam.

Instead, this course will review the general information necessary for your test-taking experience to go as smoothly as possible, and point you to resources you can use to study for each exam.

Free

20m

Introductory

Data Warehousing Practitioner

Building Semantic Models in Databricks with UC Metric Views

In this course, you’ll learn how to empower your data consumers to get validated business insights with less burden on you and the rest of your enterprise's data and AI team. Through building a semantic layer on top of your gold layer, you'll offer decision makers and business analysts the opportunity to explore key business performance indicators in novel ways, while still maintaining efficient data operations and enterprise-vetted metrics.

Note: For SCORM lecture files, please ensure that you close the SCORM window after completing the content. Do not click the ‘Next Lesson’ button, as doing so may prevent the SCORM module from being marked as complete.

Languages Available: English | 日本語 | 한국어

Free

Associate

Machine Learning Practitioner

Machine Learning Operations

This course will guide participants through a comprehensive exploration of machine learning model operations, focusing on MLOps and model lifecycle management. The initial segment covers essential MLOps components and best practices, providing participants with a strong foundation for effectively operationalizing machine learning models. In the latter part of the course, we will delve into the basics of the model lifecycle, demonstrating how to navigate it seamlessly using the Model Registry in conjunction with the Unity Catalog for efficient model management. By the course's conclusion, participants will have gained practical insights and a well-rounded understanding of MLOps principles, equipped with the skills needed to navigate the intricate landscape of machine learning model operations.

Note:

1. This is the fourth course in the 'Machine Learning with Databricks’ series.

2. For SCORM lecture files, please ensure that you close the SCORM window after completing the content. Do not click the ‘Next Lesson’ button, as doing so may prevent the SCORM module from being marked as complete.

Free

Associate