Contents
Table of Contents
- Part I — FoundationsChapter 1Tokenization and the Cost of a Request
The exact token count Claude actually bills for, and what that costs to call.
- Chapter 2Large Language Models
How a model turns a prompt into a reply, one token at a time.
- Chapter 3Retrieval-Augmented Generation
Teaching an AI to look things up before it answers.
- Part II — Applied TechniquesChapter 4AI Agents and Tool Use
Watching an AI decide, act and use outside tools on its own.
- Chapter 5Automatic Text Summarization
Ranking a document's own sentences to condense it, without inventing a word.
- Chapter 6Semantic Caching
Skipping a model call entirely when a new question means the same thing as an old one.
- Chapter 7Evaluating AI Outputs
Scoring an answer against a reference instead of just eyeballing it.
- Part III — Beyond the ModelChapter 8These Concepts in the Real World
Real companies, real numbers: how this stuff is actually used at scale.
- Chapter 9The System Behind This Tutorial
A behind-the-scenes tour of the system running these chapters.
- Chapter 10A Personalized, Diagram-Based Explainer
Ask your own question and get back a real diagram and explanation built just for it.
- Chapter 11How This Tutorial Was Built
The story of how an AI coding assistant and a person built this, together.