Three prompts. Guess the next token before the model reveals its odds. Score 3/3 and you are the autocomplete.
you_are_the_model · round 1/3
The capital of Tamil Nadu is
ChatGPT’s entire job: pick the next token. Your turn — tap your guess.
the_deal
Walk out with six things you built.
Every session ends with working code in your hands, not notes about someone else's code.
S1
Your first AI script
Your own API key, your own code, calling a frontier model — before you leave the first session.
S2
An eval harness
A tester that measures whether AI answers are right — like an engineer, not a fan.
S3
A vision app
Upload a photo, interrogate it. AI that reads documents, receipts and handwriting.
S4
Chat with your notes
An AI that answers from your study material — RAG, the pattern behind most real AI products.
S5
A tool-using assistant
AI that calls tools your code controls — and the judgment to know when not to build an agent.
S6
A hardened capstone
You attack each other's apps, patch the holes, and demo a real product to the room.
no_hidden_jargon
The whole syllabus, said plainly.
If a concept matters in real AI engineering, it's named here up front: taught from scratch, then used in a lab the same afternoon. Hover any chip: a course that can't define its vocabulary in one plain line doesn't own it.
tokenizationembeddingsattentionsoftmax & temperaturetraining vs inferencecontext windowsprompt anatomyfew-shothallucination mechanicseval harnessesscorers & test setsvision tokensdiffusionvoice cloningsemantic searchchunkingRAGgrounded promptsfunction callingthe agent loopworkflows vs agentslocal modelsprompt injectiondefense in depthtoken economicsstructured outputsreasoning modelsMCPmulti-agent systemsresponsible AI
the_format
One weekend. A rhythm, not a lecture.
day_1 · sessions 1–3
Understand the machine
Next-token prediction, prompting and evals, vision and images. Overnight: bring your own documents for Day 2.
day_2 · sessions 4–6
Arm it, then ship it
RAG on your own notes, tool use and agents, security and production — ending in capstone demos.
every session, the same rhythm
hook
talk · live demos on every idea
50-min lab
show&tell
Half the course is laptops-open lab time. The talks exist to make the labs land — not the other way around.
the_sessions
Six sessions, one throughline.
Predict→Measure→See→Know→Act→Ship
Each session hands its verb to the next. By Sunday evening the sentence is yours.
Next-token prediction, tokens, embeddings, attention, training vs inference — the whole engine, every idea a live demo, including a neural network you watch think.
Colab notebooks for all six labs ship in the labs/ folder of the course repo.
the_arguments
Every session stops once to pick a fight.
One deliberately debatable claim per session, defended on stage. The deck goes lights-off for it. Disagreement is part of the syllabus; the strongest counter-argument gets named on the closing slide.
session_1
If autocomplete can pass your exam, your exam was never testing understanding.
session_2
Hallucination is not a bug. It is the model doing exactly what it was trained to do.
session_3
Your mother's voice is no longer proof of your mother.
session_4
Your final-year project is one grounded prompt away from being a startup.
session_5
Most production "AI agents" are a while-loop in a trench coat.
session_6
There is no secure AI agent. Only one whose blast radius you've made small enough to survive.
the_method
Why it's built this way.
This course exists to prove a point about teaching AI, and it wants to be copied.
Vote before the reveal
Every big idea arrives as a game: the room predicts, shouts, commits — then the answer lands. A brain that guessed wrong remembers forever.
Build before the jargon
Raw API calls before frameworks, your own retrieval loop before "vector database" is ever said. You earn every abstraction before you're allowed to use it.
Honest failure is curriculum
Demos that can fail live stay in the deck. Hallucinations get measured, not apologized for. The fine print is taught with the magic.
Measure, don't vibe
"It worked when I tried it" is not evidence. From Session 2 onward, every claim about AI quality must survive an eval.
If you only listen, you forget. Here, everyone ships — in every session, on any laptop, for free.
your_instructor
Built by someone who ships this for a living.
Karthikeyan NG heads engineering at Vision, a fintech and crypto platform in Dubai — where RAG pipelines, eval harnesses and agent guardrails are production reality, not slideware. Along the way: two startups founded, two published books on machine learning, eighteen hackathon wins, and stages at TEDx, Google, IIT Kharagpur and Seoul.
The course began where you might be sitting now — an engineering classroom (CSE '09, Madurai). He built the course he wishes he'd had, and credits most of what it teaches to the hundreds of things he shipped that failed.
Six interactive decks, six labs with notebooks and handouts, six cheatsheets, a complete learning guide, per-slide timing, and instructor prep packs. Swap Madurai for your city and run it anywhere.
Presenting? Open any deck and press S for presenter mode — a live timer, per-slide budgets, a pace badge, and speaker notes. Arrow keys navigate · F fullscreen · O overview grid.
questions
The ones everyone asks.
Does it really cost nothing?
Yes. The labs run on Google AI Studio's free tier (no credit card) and free Google Colab. The whole course fits inside the daily free limits — the lab handouts even budget the API calls per exercise.
What laptop do I need?
Anything that opens a browser. All heavy computation happens in Google's cloud; your machine just needs a keyboard and Wi-Fi. A ₹15,000 laptop is exactly as capable here as a MacBook Pro.
Do I need math or ML background?
One line of school math appears in the whole course: y = wx + b. If you can write a for-loop in any language, you have every prerequisite.
Can I self-study without an instructor?
Yes. The decks are self-contained and interactive, every lab has a step-by-step handout with checkpoints, and pressing S in any deck shows the full speaker narration. The Learning Guide covers every concept in prose.
Is my data private on free tiers?
Assume free-tier conversations may train future models. The course drills one rule from Session 1: never paste anything you couldn't survive seeing on the front page of the newspaper.
Can I teach or translate this?
Please do — that's the point. Teach This Yourself covers running it at any scale, and the Madurai references are designed to be swapped for your own city's.
