AI / ILLUSTRATED SERIES

Illustrated LLM Engineering

Tokens, Embeddings, and RAG from First Principles

Build a support assistant that can look up information and use tools. Learn how tokens, embeddings, and retrieval work, and test the answers it gives.

Coming soon

We’re preparing this book for publication. Its Amazon listing will be linked here when it’s available.

Read a sample chapter

A REAL LOOK INSIDE

What a Language Model Actually Is

Otto will draft support replies, retrieve documents, and request tools. This chapter isolates one operation used during text generation: given the available context, a model assigns scores to possible next tokens. A decoding procedure selects a token, appends it, and repeats.

That account is useful but deliberately incomplete. Deployed models may accept images or audio, perform hidden or exposed reasoning, and use provider-specific processing around generation. The application still receives an autoregressively generated token sequence, but the visible reply is not necessarily the model's only computation.

An excerpt from the working manuscript. Read the illustrated pages or download the complete sample chapter.

Read the sample →

First page of What a Language Model Actually Is, a sample from Illustrated LLM Engineering

A LITTLE MORE CLARITY

What you’ll explore.

Developers who can call an API and want to build more dependable LLM applications.

The outline is from the working manuscript and may change before publication.

01Tokens and context
02Embeddings
03Retrieval
04Tool use
05Evaluation
06Application design

PUT AN IDEA TO WORK

There’s a seat for your curiosity.

Try a coding problem, then compare approaches with a friend.

Explore practice

Opening your workspace…