The Grounded-Builder Track · High School · 10 hours

AI Builders

25% understand. 75% build. Learn just enough of what’s under the hood to never be fooled — then spend the rest shipping real AI products in a STEM or business field you care about, with guardrails that keep it honest.

See how it works →
The bet

You don’t need to be a mechanic to drive — but you can’t know nothing

The fastest way to lose a class is “math first, cool stuff never.” The fastest way to create fragile builders is “ship magic you can’t explain.” This track threads the needle: a short, vivid foundation that kills the magic and installs a BS-detector, then four weeks of building real things with AI — where you must measure, break, safeguard, and defend everything you ship.

The one principle: AI gives you leverage; understanding gives you judgment. Leverage without judgment ships confident nonsense. This track keeps them together — you build fast and you can defend every number.
The 25 / 75 split · 10 hours

A quarter to understand, three-quarters to build

25%≈ 2.5 hrs · GROUNDkill the magic
75%≈ 7.5 hrs · BUILDship a real product with AI, with rigor

The grounded 25% isn’t a lecture — it’s the smallest set of hands-on truths that make you impossible to fool: features/label/loss, the train/test split, bias you can measure, and “plausible ≠ true.” Then you spend the 75% where the motivation (and the resume) actually is: building.

Choose your path

Which bootcamp is for you?

Both are great. Pick by where you’re headed.

🐍 AI Trailblazers (Python-first)
⚡ AI Builders (grounded-builder)
You want to understand AI deeply, from the code up
You want to build real things AI can power, fast
Future: engineer, ML researcher, CS major
Future: founder, doctor, scientist, designer, analyst
Write every line of Python yourself
Direct AI to write code; you spec, evaluate & fix
Ship: a classifier, a language model from scratch
Ship: a working product people can actually use
~80% under the hood, ~20% build
~25% under the hood, ~75% build
Honest truth: the strongest builders eventually want some of both. Start where your fire is — you can always cross over. (Ready for the deep one? AI Trailblazers →)
The Trail · 5 sessions × 2 hrs

One week to get grounded, four to build

1GROUND

Kill the Magic the 25%

One fast, hands-on session: train a tiny model, measure it honestly, produce & catch bias by hand, and see why fluent AI can be confidently wrong. You leave with a BS-detector — enough to never be fooled by an AI, or by your own demo.

2BUILD

Pick Your Arena build

Explore how AI is remaking real fields (see AI across STEM & Business →), choose a domain and a real user with a real problem, and scope your build with the canvas. Data + rights checked up front.

3BUILD

Build the MVP with AI build

“Vibe coding” done right: describe what you want, let AI draft the code, run it, read the errors, iterate. Ship a working prototype end-to-end. Ugly is fine; running is required.

4BUILD

Make It Honest build + rigor

This is where building earns its rigor: measure a real number, red-team your own product until it breaks, add one safeguard, and be able to explain every part. “The AI wrote it” is not an answer.

5SHIP

Ship & Show ship

A public 3-minute, 4-beat demo with one real artifact and your number said out loud. Walk away with a shipped product, a resume bullet, and a certificate.

The Rigor Guardrails

Five rules that keep vibe-building from going hollow

Building fast with AI is a gift — and a trap. These five non-negotiables import the discipline of a real engineer into the speed of a vibe coder. Every capstone must pass all five.

  1. Measure a real number.

    Accuracy, recall, pass-rate, a user metric — something on a held-out test, not a vibe. If you can’t measure it, you can’t claim it.

  2. Red-team it before someone else does.

    A pod-mate tries to break your product — wrong inputs, edge cases, prompt injection. You fix what they find.

  3. Build one safeguard.

    A threshold, a refusal, a dry-run confirmation, a “not medical advice” note. Name the harm you anticipated and the guard you built against it.

  4. Defend every part.

    You must be able to explain what each piece does — even the code AI wrote. If you can’t explain it, you don’t ship it.

  5. Cite your data & rights.

    Where did the data come from? Do you have the right to use it? Whose privacy is involved? Answer before you build.

The builder’s law
If you can’t defend the number, you didn’t build it — you summoned it.

Leverage is only yours if you can stand behind what it produced.

Badges & Toolkit

Earn one a week

🕵️

BS-Detector

Wk 1 — trained & measured a model, caught bias by hand, can spot a confident-but-wrong AI.

🧭

Domain Scout

Wk 2 — picked a real arena, a real user, and scoped a build with data rights checked.

🔨

AI Builder

Wk 3 — shipped a working MVP end-to-end using AI, and can explain how it works.

🛡️

Rigor Keeper

Wk 4 — measured a number, red-teamed it, and built a safeguard that works.

🚀

Shipped-It

Wk 5 — public demo with one artifact + a resume bullet with a real number.

🏆

Grounded Builder

All 5 badges + all 5 guardrails passed on your capstone.

Your toolkit

🤖

AI copilots

Claude, ChatGPT, Gemini — your build partner and explain-only tutor.

🧱

Vibe-build tools

Replit, Lovable, Cursor, v0, Claude Artifacts — describe it, ship it.

📓

Colab (light)

Just for Week 1’s grounded foundation — enough Python to not be fooled.

🌐

Gradio / HF Spaces

Turn your build into a public web demo people can try.

🧙

Gandalf

Learn to red-team — break AI safely before you defend your own.

🔬

Domain tools

Whatever your field needs — librosa (audio), MediaPipe (pose), public datasets.

Explore AI across STEM & Business →