Generative AI for Data Engineers: From Basics to AI Agents

Lesson 1: GenAI - For Data Engineers Agenda & Introduction | LLM & Agentic AI | LangChain & LangGraph | Claude

This introductory video outlines the full GenAI course agenda for data engineers. It explains what the course covers, including LLMs, agentic AI, LangChain, and LangGraph. Use it to understand the learning path and what to expect in later chapters.

Play lesson

Lesson 2: From AI to Agents| Fundamentals of AI | ML | DL | LLM & GenAI | Chapter 01

Chapter 01 explains the fundamentals of AI and how its subsets differ. It covers machine learning, deep learning, LLMs, and generative AI at a high level. This gives you the vocabulary needed for the rest of the course.

Play lesson

Lesson 3: Machine Learning Explained - END to END | Chapter 02

Chapter 02 walks through machine learning end to end. It covers features and labels, supervised versus unsupervised learning, feature engineering, and model accuracy. Classification and regression are explained with simple examples.

Play lesson

Lesson 4: Neural Networks Explained - How They Work & Are Trained | Chapter 03

Chapter 03 explains how artificial neural networks work and how they are trained. It covers activation functions, forward and backward propagation, gradient descent, and hyperparameters. The explanations use simple examples and avoid heavy math.

Play lesson

Lesson 5: How Large Language Models (LLMs) Work - Full Explanation | Chapter 04

Chapter 04 gives a full explanation of how large language models work. It covers tokens, context length, transformers, sampling, and fine-tuning. The chapter uses simple examples and avoids heavy math.

Play lesson

Lesson 6: How LLMs Understand your Prompts: Tokenization & Embeddings | Chapter 05

Chapter 05 explains tokenization and vector embeddings and how they let an LLM capture meaning. It covers vector dimensions, cosine similarity, and positional embeddings. A hands-on coding demo shows these concepts in practice.

Play lesson

Lesson 7: How Transformers Work - Attention Explained Step by Step | Chapter 06

Chapter 06 breaks down the transformer architecture step by step. It explains attention, the difference between encoder and decoder, and next-token prediction. The chapter is presented in plain English without scary math.

Play lesson

Lesson 8: How to Write Efficient Prompts | Prompt Injection Attacks | Chapter 07

Chapter 07 covers prompt engineering from the ground up. It explains how to write prompts that produce reliable output and demonstrates two real prompt injection attacks that can leak sensitive data. The chapter focuses on practical prompt design and security awareness.

Play lesson

Lesson 9: RAG Explained + Build a RAG App From Scratch in Python using LLM | Chapter 08

Chapter 08 explains Retrieval-Augmented Generation (RAG) end to end. It then builds a working RAG application from scratch in Python without using LangChain or a vector database. This hands-on chapter shows how retrieval and generation fit together.

Play lesson

Lesson 10: Build Your First AI Agent + LLM Tool Calling Explained | Chapter 09

Chapter 09 introduces AI agents and explains LLM tool calling. It describes an agent as a model (the brain) plus tools (the hands) and walks through the tool calling loop from user message to final answer. You build your first AI agent in this chapter.

Play lesson

Lesson 11: LangChain Tutorial - Build an AI Agent with Tools | Chapter 10

Chapter 10 is a hands-on LangChain tutorial. It starts with a plain LLM call and builds up to a full agent with tools, memory, and a sub-agent in a few lines of Python. This chapter rebuilds the agent from Chapter 9 using LangChain.

Play lesson