How AI Actually Works

Ever wondered how a machine learned to talk? It started with a guessing game.

This friendly, generously illustrated guide opens the box on large language models — no math degree required, just curiosity. Predict the next word, check, adjust, repeat — trillions of times. From that one game, this book builds up the full machinery: tokens and embeddings, the Transformer and attention, how models are trained, and why scale changed everything.

Then it turns practical: the craft of prompting and context engineering, retrieval (RAG), tools, MCP, and AI agents; how to choose a model without the hype; your first API call; and the judgment to use AI responsibly — hallucinations, bias, and privacy included.

With 70+ hand-drawn diagrams, chapter glossaries, a reusable prompt template, cheat sheets, and a full glossary index, this is the beginner's book that treats you like an adult — and leaves the black box open.

Book 1 of the Tech Guides: LLM Series.