1
ConceptsChapter 1 of 5
Tokens
The thing AI charges for.
TL;DR
The fundamental unit that LLMs read and generate · 1 token ≈ 0.75 English words or 4 characters.
“Tokens are the units of AI billing. Understand them or overpay.”
Read full chapterLearning path5 terms · ~15 min read
What is GenAI · for normies
Zero jargon. Six terms to sound smart at a dinner party.
2
ConceptsChapter 2 of 5
Transformer
The idea behind every modern AI.
TL;DR
The 2017 "Attention Is All You Need" architecture · parallelizable, scalable, and the foundation of every modern LLM.
“The transformer is 8 years old and shows no signs of being replaced. Every proposed successor so far adds complexity without killing the scaling-law champion.”
Read full chapter3
ConceptsChapter 3 of 5
Inference
What happens every time you use AI.
TL;DR
The process of running a trained model to generate predictions · every API call is inference.
“Inference optimization is where the next 10× cost reduction lives. Every frontier lab is racing to ship the best serving stack.”
Read full chapter4
ConceptsChapter 4 of 5
Prompt Engineering
Why typing matters.
TL;DR
Crafting inputs to LLMs to get better outputs · few-shot examples, chain-of-thought triggers, role assignment, structured formats.
“Prompt engineering as a standalone job is done. Prompt engineering as a skill is table stakes. Know what structured outputs are and move on.”
Read full chapter5
ConceptsChapter 5 of 5
AI Agent
Where AI is going next.
TL;DR
An AI that plans multi-step workflows, uses tools, and maintains state · not a single-turn chat.
“Agents are where the frontier is in 2026. Chat is a solved problem. Agents are where the next decade of AI revenue compounds.”
Read full chapterWhat you learned
By the end you know what tokens, training, inference, and agents actually are · and you can hold your own in any AI conversation.
Keep learning
Next path · 7 terms
The AI Bubble Explained
Seven terms that decode whether AI is overpriced, fairly priced, or criminally underpriced. Read in order.