← Back to QuantegyAI

Intro to AI

Learn the core AI skills — and finish by building a small app of your own.

Track your progress. Sign in to save lesson completion and scores, submit your capstone, and earn a certificate. Teachers can create a class and watch student progress. Open the portal →

This short track takes you from "what is an AI assistant?" to actually shipping something with one. The lessons teach skills that work with any AI tool — Claude, ChatGPT, Gemini, and others. Then a hands-on capstone puts them to work: you will build and ship a small interactive app, start to finish.

Short, hands-on lessons (a few minutes of reading each) plus the capstone project. No coding background assumed.

Lessons

Lesson 1

What AI Assistants Actually Are

Hands-on: predict, sort, and self-check your way through how large language models work — what Claude, ChatGPT, Gemini, and Copilot have in common, and where they fall short.

Lesson 2

How AI Predicts the Next Word

Hands-on: the same blank, two different sentences — and why your best guess flips. Meet conditional probability, the simple "given what you already know" idea that drives every answer an AI gives.

Lesson 3

Working with an AI Assistant

Hands-on: how to direct an AI on a real project — giving context, scoping tasks, pausing before risky changes, and checking the result against what the AI claims.

Lesson 4

Prompting Well and Checking the Output

Hands-on: the two skills that matter most — writing a clear prompt, and never trusting an answer you have not verified.

Lesson 5

From Idea to a Working MVP

Hands-on: how a small app goes from a rough idea to something real — defining the smallest useful version, planning steps, building, testing, and iterating.

Capstone project

Build it

Build a Concept Manipulative

Apply everything: build a small single-page interactive app that explains one concept of your choice, taking it through the full lifecycle — idea, MVP, build, test, ship.

Use AI as a collaborator, not an oracle. These tools draft fast and explain well, but they also make confident mistakes. Your job is to direct the work and check it — and by the capstone, to ship something real with it.
Next course → Math Foundations for AI — eight interactive modules on the math behind machine learning: notation, probability and Bayes, vectors and matrices, gradient descent, and statistics, each tied to how real models work. No STEM degree required.

← Back to QuantegyAI