Skip to main content

Foundations Overview

Who this is for​

Zero prior AI knowledge assumed. If you've never trained a model, never called an API, maybe never even written a line of Python, you're in the right place. The only thing you need is a computer and the willingness to type commands into a terminal, which Chapter 0 walks through step by step.

What this track covers​

Foundations builds up one idea at a time, in the order you actually need them: what "AI" and "generative AI" even mean, how a large language model predicts the next word, how to phrase a prompt so the model does what you want, how to turn text into a form a computer can search (an embedding), how to store and search those embeddings at scale (a vector database), how to combine search and generation so a model can answer questions about your own documents (RAG), and what it means to give a model the ability to reason and act on its own (an agent).

Every chapter pairs a plain-language explanation with a small, hands-on lab you run yourself, on your own machine, for free.

What you'll be able to do by the end​

By the end of Foundations, you'll have built a working Q&A bot that answers questions over your own documents, and you'll understand every piece it's made of, not just how to copy-paste a tutorial. That bot is the capstone of Chapter 8, and it's the foundation Intermediate builds on next.

The chapters ahead​

  1. Set up your machine — install the free tools every later lab depends on.
  2. What is AI? — where generative AI fits inside AI and machine learning.
  3. What is an LLM? — how a large language model predicts the next word.
  4. Prompting 101 — how phrasing changes what a model produces.
  5. What is an embedding? — turning text into something a computer can compare.
  6. What is a vector database? — storing and searching embeddings at scale.
  7. What is RAG? — combining search and generation to answer questions about your own documents.
  8. What is an AI agent? — giving a model the ability to reason, act, and loop.
  9. Capstone — a working Q&A bot over your own documents, built from everything before it.

There's also a short, optional bonus chapter tucked in right after Chapter 2: using AI responsibly, privacy, bias, and verifying what a model tells you.

What's next​

Chapter 0 starts with the boring-but-necessary part: getting the free tools installed so every later chapter just works.