Building Persistent Memory for AI Agents with Lakebase on Databricks

This course teaches how to build AI agents that remember — both within a conversation and across sessions — using Databricks Lakebase as the persistence backend. Students learn how LangGraph’s Checkpointer system provides short-term memory (within-session conversation continuity) and how LangGraph’s Store provides long-term memory (cross-session user preferences), both backed by Lakebase Autoscaling. Students build and test these memory systems in notebooks, observe agent behavior through MLflow traces, and deploy a fully stateful agent as a Databricks App.

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.

Skill Level

Associate

Duration

Prerequisites

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

General familiarity with Databricks workspace, Unity Catalog experience, AI agent building experience, basic Python proficiency. Lakebase and Databricks Apps introduced at overview level only.

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

Vibe Coding a Databricks App

This is a hands-on course that shows learners how AI-assisted development can accelerate the journey from an idea to a functional application. Participants use Databricks Genie Code to turn plain-language ideas into a working Databricks App, then iteratively refine the app by identifying issues, improving prompts, and applying production-oriented best practices.

Paid & Subscription

Lab

Professional

Context Is Everything: Lakebase Agent Memory

Build a complete, stateful LangGraph agent and deploy it as a Databricks App. You'll create an assistant that answers business questions by calling Unity Catalog function tools over live data, sustains multi-turn conversations through short-term checkpointed state, and recalls each user across sessions days apart via persistent long-term memory. Along the way you'll see why context is everything: an agent is only as good as the context assembled into its prompt, and memory — backed by Lakebase Postgres — is how that context survives beyond a single inference.

No Code ETL with Lakeflow Designer

This course introduces Lakeflow Designer as a no-code, AI-assisted ETL experience on Databricks and walks learners through building an end-to-end medallion architecture pipeline. Participants explore source data, ingest files and tables, build bronze, silver, and gold layers using visual operators, natural language with Genie Code, and SQL where needed, then validate outputs and schedule workflows for production-ready execution in Unity Catalog.

Paid & Subscription

Lab

Professional