NorthGradient
Start reading

The library

Pick a track to see its full contents.

Short course · intro

Neural Networks

Build a neural network from its smallest piece, one neuron at a time.

9 parts · ~51 min View contents →

Course · intro

How Language Models Actually Work

A first-principles path through tokens, embeddings, attention, and the machinery behind LLMs, built up step by step.

15 lessons · ~83 min View contents →

Course · intro

Prompt Design

Write prompts that get reliable, repeatable output from any language model: the anatomy of a prompt, clear instructions, roles, and in-context learning, from first principles.

15 lessons · ~85 min View contents →

Short course · intro

Introduction to LLM Agents

Build a working agent from scratch in plain Python, one piece at a time: a tool, the reasoning step, the call, and the loop. Then see where plain loops break and why frameworks exist.

7 parts · ~31 min View contents →

Short course · intermediate

Building Production Agents with LangGraph

Take a working agent and make it hold up in production: clean state, explicit graphs, reliable tools, recoverable failures, and the observability and hygiene that keep it maintainable.

9 parts · ~60 min View contents →

Paper explainer · intermediate

Attention Is All You Need

A visual, plain-language walkthrough of the 2017 paper that introduced the transformer, from the limits of RNNs to the architecture behind every modern LLM.

9 parts · ~27 min View contents →

Short course ☕ Brewing

Diffusion & Image Models

How models paint a picture by reversing noise, step by step.

Coming soon

Short course ☕ Brewing

Retrieval-Augmented Generation

Give a model your own documents so its answers stay grounded in your facts.

Coming soon

Course ☕ Brewing

Training & Fine-Tuning

How models learn from data, and how to adapt a pretrained model to your own task.

Coming soon