One nesting map
AI, ML, deep learning, generative AI and LLMs, in their place.
What you’ll learn
Four ideas, one module
Model vs product
Same model, different products, different failures.
Training vs inference
Why your chat doesn’t teach the model.
The system map
Eight boxes you’ll use for the rest of the course.
The system map
Eight boxes around one model
Context
What the model sees right now
Knowledge
Documents and retrieval
Memory and state
What persists between turns
Tools and actions
What it can do in the world
Model
Generates the next tokens
Orchestration
Steps and loops around calls
Guardrails
What it may see and do
Evaluation
How we know it works
Interface
Where people meet it
Every later module zooms into one box.
Applied exercise
Dissect three real products
Dissect ChatGPT, a coding assistant and a support bot into model, context, tools, state and external systems.
- ChatGPT
- A coding assistant
- A customer-support bot
Cheat sheet
Most of what users call “the AI” is the system you build around the model
One page you keep: the questions to ask on every project, the rules of thumb, and a checklist you can use on your own product. All ten come with The Book.
Leave at the door
Five myths this module breaks
| Myth | What’s actually true |
|---|---|
| “The model learns from my chats.” | Weights don’t change during inference. |
| “It looks things up to answer.” | Only if the system gives it a search tool. |
| “Better prompts are the main lever.” | Context, data and tools usually matter more. |
| “The demo worked, so it works.” | A demo is one sample, not an evaluation. |
| “The AI decided.” | Someone configured that behavior. |
Before you move on
Can you call this one?
A support bot starts quoting outdated refund terms.
Name three places the problem could be. Which one is the model?
How we would answer
- Knowledge an old policy document or a stale retrieval index.
- Context the system instructions still quote the old terms.
- Memory a cached answer or saved note repeats them.
- Tools a policy API or database returns old data.
- Model the terms came from training data before the knowledge cutoff. Only this one is the model.
Every module ends on a question like this. Join the waitlist →
The Stack Surgeon
Jax Ellery
dissects AI products layer by layer to expose what is actually intelligent and what is just clever engineering.
Episode 01 · What is an AI system?
Included with the course.
Coming soon · an AI character from the show, not a real researcher.
Next · Module 02