AI courses you can
finish in less than an hour

Courses that build real intuition for how AI works, one scroll-driven animation at a time. Pick where to start.

Free, without ads and no signup required.

6 chapters

Build an AI Agent (AI Agents)

Give Claude a loop and real tools, and watch it plan, act and finish a task on its own — in Python, in about half an hour.

Start the course→
6 chapters

The Three Ways Machines Learn (Supervised, Unsupervised & RL)

The real difference between supervised, unsupervised and reinforcement learning — in about half an hour.

Start the course→
13 chapters

From Pixels to Predictions (Computer Vision & CNNs)

Understand neural network foundations in less than an hour.

Start the course→
7 chapters

How Tesla Self-Driving Works (Autonomous Driving)

How eight cameras and a neural net turn a car into a driver — in about half an hour.

Start the course→
7 chapters

How Machines Understand Meaning (Embeddings)

How AI turns words into points in space — the idea behind search, recommendations and RAG.

Start the course→
6 chapters

Learn NumPy by Doing (NumPy)

The array library behind all of Python's data and AI world — learned through fun exercises, in about half an hour.

Start the course→
6 chapters

Learn pandas by Doing (pandas)

The table library every data analyst and data scientist reaches for first — learned through fun exercises, in about half an hour.

Start the course→
6 chapters

Your First PyTorch Project (PyTorch)

Install PyTorch and train a real neural network to read handwritten digits — in about half an hour.

Start the course→
6 chapters

Build a Semantic Search Engine (Embeddings & Semantic Search)

Search text by meaning, not keywords — build a working semantic search engine in about half an hour.

Start the course→
6 chapters

Build a RAG Chatbot (Retrieval-Augmented Generation)

Make a chatbot that answers from your own documents — fully on your laptop, in about half an hour.

Start the course→
6 chapters

A Neural Net From Scratch (Backpropagation in NumPy)

Build and train a neural network with nothing but NumPy — and finally see what PyTorch's autograd hides.

Start the course→
6 chapters

Build a Tokenizer From Scratch (Byte Pair Encoding (BPE))

Build the byte-pair encoding tokenizer behind GPT — in pure Python, in about half an hour.

Start the course→
6 chapters

Build a Movie Recommender (Collaborative Filtering)

Build the 'people like you also watched' engine behind Netflix — in NumPy, in about half an hour.

Start the course→
6 chapters

Your First Claude API App (The Claude API)

Build a streaming, tool-using chatbot on the Claude API — in Python, in about half an hour.

Start the course→
6 chapters

Build an MCP Server (Model Context Protocol)

Package your own tools and data as a server any AI app can plug into — in Python, in about half an hour.

Start the course→
6 chapters

Getting the Most out of ChatGPT (Using ChatGPT Effectively)

Not how it works — how to actually use it well. Practical habits for real tasks, in about half an hour.

Start the course→
6 chapters

Getting the Most out of Claude Code (Claude Code)

Not a feature tour — the habits that make an AI coding agent actually productive, in about half an hour.

Start the course→
7 chapters

How ChatGPT Actually Works (Large Language Models)

The one trick behind every chatbot: predicting the next word — in under half an hour.

Start the course→
7 chapters

From Noise to Images (Diffusion Models)

How AI turns random static into a picture — in about half an hour.

Start the course→
7 chapters

How Your Feed Knows You (Recommender Systems)

How apps pick, from millions of posts, the handful you actually see — in about half an hour.

Start the course→
7 chapters

CPUs, GPUs & TPUs (AI Hardware)

Why AI runs on GPUs and TPUs instead of the CPU in your laptop — in about half an hour.

Start the course→
7 chapters

Why Captchas Show You Traffic Lights (CAPTCHAs)

The web's human-vs-bot test — and why solving it quietly trains AI — in about half an hour.

Start the course→
6 chapters

What Inference Really Is (AI Inference)

What actually happens when an AI model runs — not how it's trained, but how it's used. In about half an hour.

Start the course→
6 chapters

How AI Pays Attention (Transformers & Attention)

The one idea behind every modern AI model — attention — visualized from scratch, in about half an hour.

Start the course→
6 chapters

How a Network Actually Learns (Backpropagation)

How a network turns 'that's wrong' into a fix for millions of weights — the backprop algorithm, visualized.

Start the course→
6 chapters

How to Talk to an AI (Prompt Engineering)

Why the same AI gives one person gold and another mush — the craft of writing effective prompts, in about half an hour.

Start the course→
6 chapters

The Price of a Prompt (AI Cost Optimization)

Why AI bills explode — and the five levers that cut them 10× — in about half an hour.

Start the course→
Ankur Datta
Built by Ankur Datta
Connect on LinkedIn →

Privacy