AI in the Flow of Data Engineering: 5 Days to Build Data Pipelines with Databricks Genie Code

The new Databricks Genie Code agent has the ability to transform how data engineers build and manage pipelines—but most practitioners haven’t yet had a chance to apply it in a real workflow. In this hands-on five-day challenge, Baraa Salkini guides you through using Genie Code inside Databricks to build a complete data pipeline using the free samples.tpch dataset. Each day focuses on a core layer of modern data engineering, from ingesting raw data to transforming it into business-ready insights. Along the way, learn how to use AI to generate code, accelerate development, and troubleshoot issues in real time. By the end of the challenge, you have a working pipeline you can share, extend, and build on in your own projects. This course is designed to be fully accessible using Databricks Free Edition, so you can follow along at no cost.

Learning objectives
Build a multi-layer data pipeline (Bronze, Silver, Gold) using Databricks and Genie Code.
Use AI-assisted workflows to generate, refine, and debug data engineering code.
Transform raw data into structured datasets and business-ready metrics using modern data engineering patterns.
Orchestrate and operationalize a simple data pipeline, including scheduling and sharing outputs.
Apply AI agents to accelerate common data engineering tasks, from ingestion to analytics.