New Course — NovaGlyph Kit

The Grammar of
Intelligence

Learn how AI actually works — from the inside. You write the facts. You compile them. You ship a working offline AI that fits in a text message. No Python. No maths prerequisites. No GPU. No cloud.

6 sessions, ~3.5 hours total
macOS 13+, any Mac
No prerequisites
Free with Kit purchase
first_aid.light — your first Baby AI
-- KNOWLEDGE — the brain. Edit these freely. FACT burn CAUSE "cool with running water for 20 minutes" FACT cut CAUSE "apply firm pressure with a clean cloth" FACT choking CAUSE "5 back blows then 5 abdominal thrusts" -- INHERITANCE — one fact answers many questions FACT sunburn TYPE_OF burn FACT papercut TYPE_OF cut -- compile: ./bin/lightc first_aid.light -- run: ./templates/first_aid > sunburn cool with running water for 20 minutes > shark_attack I don't know that one yet — teach me by adding a FACT

What You Build

Six sessions. Six things you ship.

Every session ends with a working artifact. Not a slide. Not a quiz. Something you compiled and ran.

🧠

A personalised Baby AI

Your first compiled binary — a First Aid Baby with facts you chose and added yourself. Runs offline on any Mac.

🧬

An inheritance hierarchy

A TYPE_OF chain in your own domain. One fact answers dozens of questions it was never explicitly taught.

🔧

A debugging worksheet

Three deliberate breaks. Three diagnoses. Three fixes. You will understand compiler errors and runtime gaps.

🧬

An evolution assessment

A written analysis of a machine-proposed mutation — is it correct? Would you authorise it?

🛡️

An AI Safety Incident Report

You encounter the Gatekeeper. You type CANCEL. Then AUTHORIZE. You write who is responsible for the outcome.

📦

Your domain Baby

A compiled binary in a domain you know. A peer runs it without the compiler. You ship software on the last day.

The Six Sessions

What happens in each session

Each session is self-contained. They stack — each one builds on the last — but the course works in a classroom, online, or self-paced.

1

Your First Baby AI

Install the Kit, compile first_aid.light, ask it questions. Then add three facts of your own. Recompile. Test them.

FACT CAUSE lightc compiler knowledge-based AI
45 min
2

Teaching Inheritance

Add TYPE_OF chains. Watch the Baby answer sunburn by looking up burn — without a sunburn fact. Build a 2-hop chain.

TYPE_OF inheritance recursive reasoning
30 min
3

When the Baby Fails

Break it deliberately — missing quotes, duplicate facts, unknown queries. Fix each one. Understand why "I don't know" is safer than a guess.

debugging compile errors graceful failure
30 min
4

The Evolution Engine

Run evolve-baby.sh on a gap in your Baby. Watch the computer propose a new fact. Read it. Decide whether it's correct before anything compiles.

genetic programming mutation fitness proposal vs decision
45 min
5

The Gatekeeper

The evolution engine pauses and shows you its proposed code. You type AUTHORIZE — or CANCEL. You write an Incident Report. You decide who is responsible.

AI safety human-in-the-loop corrigibility AUTHORIZE
30 min
6

Ship It

Write a Baby in your own domain. Compile it. Hand the binary to a peer who has no compiler. They run it. You shipped software.

knowledge engineering domain design distribution
30 min

Learning Outcomes

What you will understand
when you finish

Not knowledge you memorised. Understanding you built by doing.

The difference between a knowledge-based system and a generative language model — and when to use each

How to write, compile, and debug a Light Code program from a blank file

Why inheritance lets a small fact table answer questions it was never explicitly taught

What genetic programming means in concrete, hands-on terms — not theory

Why the Gatekeeper Protocol exists — and who is responsible for what an AI does after you authorise it

How to ship a self-contained AI binary that runs on any Mac without a compiler or runtime

Why "I don't know" is an architectural safety choice — and what it protects against

How to capture domain knowledge precisely enough that a machine can reason about it

No Python. No maths prerequisites. No GPU. No cloud. Every tool in this course runs offline on a MacBook. The compiler is 35 KB. The only thing you need to bring is a domain you know something about.

Why This Approach

Most AI courses hide
how AI actually works

This course doesn't. Every answer is traceable to a fact you wrote. Every decision is one you made.

This course Typical "learn AI" MOOC Using ChatGPT
You see how every answer is produced Yes No — theory only No
You write the AI's knowledge yourself Yes No — you train on data No
Runs offline, no subscription Yes Depends No
GPU required No Often yes Cloud GPU
Can hallucinate / make things up No — architecturally impossible Yes Yes
You ship a working artifact Yes — session 1, and every session after Rarely No
Teaches AI safety hands-on Yes — session 5 Sometimes, as theory No

Pricing

Simple, honest pricing

The course is free with the Kit. School and team licences exist because classrooms need one copy of the compiler shared across many students.

School
A$299 / year
Unlimited students, one classroom. One instructor copy of the Kit. Students compile using the shared licence. Printable PDFs and email support included.
Corporate
Enquire
Internal training, reskilling programs, AI literacy workshops. Includes trainer-of-trainers session and customised workbook.
University
Enquire
Semester-length expansion, assessment rubrics, and bulk student licences. Academic pricing available for accredited institutions.

Start building today

The Kit ships as a download. Install takes 3 minutes on Apple Silicon. Your first compiled Baby AI takes 15 minutes. Session 1 is 45 minutes. By the end you will have written, compiled, and queried a working AI from its source code.