The Eight Words That Unlock Everything Else
You're comparing two AI tools: one was "trained on proprietary data," the other uses "a foundation model fine-tuned for your industry." You'll know what each claim actually means.
Foundations / Beginner
The Jargon Decoder
A plain-English glossary and field guide to every AI term you'll ever need — and the ones you can safely skip.
The problem
It starts with the situation you're actually in.
At some point in the last year or two, you started running into AI vocabulary faster than you could absorb it. Not just product names — technical terms people used as if they were obvious: "the model," "training data," "token limits," "prompt engineering.".
You're reading a vendor proposal and hit this in the second paragraph: "Our platform combines RAG-based retrieval with an agentic orchestration layer and a fine-tuned foundational model." You'll understand every word of it.
Outcomes
What you'll be able to do.
The Gap Between "I've Used It" and "I Can Evaluate It"
You're deciding between two AI tools — one you've used, one a colleague recommends — and both spec pages list "128K context window with adjustable temperature and support for fine-tuning." You'll know what those numbers are worth.
The Gap Between the Headline and the Paper
A company announces its new model shows emergent reasoning on a path toward artificial general intelligence. The linked paper reports a benchmark improvement on a multi-step arithmetic task, with the jump appearing sharply as model size crossed a threshold. You'll see the gap.
The Difference Between a Conversation and a Task
You type: "Check my calendar for next Tuesday, find a free two-hour slot, draft an agenda for my team meeting, and send it to my colleagues." With a basic AI chatbot, the model writes the agenda text — and nothing else. You'll know why.
Inside the book
A closer look at the work inside.
Model
After training on data, what you get is a model — the thing you actually use when you type a question into a chatbot, run a photo through a filter, or ask a recommendation engine what to watch next. Training is the cooking process; the model is the finished dish.
Model Tiers: The Names Rotate, the Categories Don't
Open any provider's model page and you'll see a short menu of options with version numbers and release dates. Those names change every few months — today's headline model is often replaced before the article falls off the front page. Chasing the names is a losing game.
Context Windows: How Much the Model Can Hold
Every LLM has a context window, measured in tokens — its working memory for a single session. Everything inside it (your system prompt, the conversation so far, the document you pasted in) is what the model can "see" when generating its next response. Anything outside the window is invisible to it.
Embeddings: How the Model Represents Meaning
When a model processes text, it converts words and phrases into numerical vectors — lists of numbers that mark where that piece of text sits in a multi-dimensional "meaning space." These vectors are called embeddings.
Fine-Tuning: Shaping a Model to Fit a Role
A base LLM is trained on general text. Fine-tuning continues that training on a smaller, specialized dataset — your company's support tickets, a set of medical records, a library of legal documents — to shift the model toward a specific domain, tone, or task.
ModelInside the book
Visual preview
A diagram you can keep open while you work.
Table of contents
6 chapters, built to be read in order.
01
Why AI Has Its Own Language
02
The Foundation Layer — Terms Every AI Conversation Needs
03
The Generative AI Layer — Vocabulary for Today's Tools
04
The Connected Layer — Agents, APIs, and the Wider Ecosystem
05
The Hype Filter — What to Believe and What to Skip
06
Your Personal Field Guide — Putting the Vocabulary to Work
100
Pages
14,656
Words
15
Exercises, checklists & tools
6
Chapters
Formats
Three formats. One purchase.
EPUB, PDF, and HTML are included so the book can work on an e-reader, as a designed copy, or as a searchable desk reference.
EPUB
For e-readers and reading apps.
The designed edition with diagrams and layouts intact.
HTML
Searchable, copy-pasteable, and practical as a reference.
Complete guide
The Jargon Decoder
$6.99
Beginner guide pricing
- ✓EPUB + PDF + HTML included in one purchase
- ✓6 chapters from the complete guide
- ✓DRM-free files for your own devices
- ✓7-day refund review for duplicate purchases, access issues, wrong files, or materially defective downloads
Secure checkout / instant download / tax handled at checkout
Before you buy
Questions, answered.
Does this include the full book?
Yes. You get the complete edition, including the chapter sequence and internal materials described on this page.
Which formats are included?
EPUB, PDF, and HTML are included so you can read on an e-reader, keep a designed copy, or use the searchable browser version.
What is the refund policy?
Because this is an instant digital download, broad change-of-mind refunds are not offered after the files have been accessed. Refund requests are reviewed within 7 days for duplicate purchases, accidental purchases before access, access failures we cannot fix, wrong files, corrupted files, or pages that materially misdescribe the book.