A reference for every concept, technique, and tool you need to build with modern AI — from first principles to the LangChain, LangSmith, and LlamaIndex ecosystem.
The foundational topics that power every modern LLM and Gen AI application.
The building blocks: data, models, training, inference, and the relationship between AI, ML, neural networks, and deep learning.
Transformer-based models trained on massive text corpora to predict the next token. The engine behind ChatGPT, Claude, Gemini, and Llama.
Models that create new content — text, images, audio, video, and code — by learning the distribution of training data.
The craft of writing inputs that steer LLMs toward useful, reliable outputs.
Ground LLM responses in your own data by retrieving relevant chunks at query time and feeding them into the prompt.
LLMs that plan, call tools, and act in loops to accomplish multi-step goals.
How to measure quality and ship LLM apps responsibly.
The libraries most teams reach for when building production LLM applications.
An open-source framework for building applications with LLMs by composing models, prompts, retrievers, tools, and agents into runnable chains.
A hosted observability, evaluation, and prompt-management platform for LLM applications (works with LangChain or any framework).
A data framework focused on connecting LLMs to your private data — the most opinionated toolkit for production RAG and knowledge agents.
Applied ML/AI case studies that show how the concepts come together end-to-end.
An end-to-end ML project for detecting fraudulent transactions in highly imbalanced data — covering modeling approach, evaluation, and feature design.
Dive deeper into any topic in the full curriculum, or jump to the glossary for quick definitions.
11 sections · Updated continuously