Free AI library

Technical guidesFree forever.

177 plain-English guides, structured learning paths, and an open library — built by an independent 501(c)(3) nonprofit so anyone can understand modern AI.

177Free guides
1Topic tracks
~2 minPer guide
~6hReading time

Start here

Five outcome-based courses

Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.

Topic tracks

Browse by track

Jump into the area you care about. Every track has multiple plain-English guides.

Full library

All guides

177 of 1019 guides shown. Filter by track or search above.

Technical

Toolformer and Self-Taught Tool Use

Toolformer is a 2023 Meta AI method that lets a language model teach itself when and how to call external tools like calculators, search engines…

2 min readRead
Technical

Voyager Minecraft Agent and Skill Library

Learn how Voyager works: a Minecraft AI agent that writes code, stores reusable skills, and improves through lifelong learning without gradient updates.

2 min readRead
Technical

Generative Agents and Simulated Societies

Generative agents are AI characters powered by language models that remember, plan, and react like believable people.

2 min readRead
Technical

Episodic and Semantic Agent Memory

AI agents need two kinds of long-term memory: episodic memory for specific past events and semantic memory for general facts.

2 min readRead
Technical

Hidden Markov Models

A Hidden Markov Model describes a system that moves through hidden states you cannot see directly, emitting observable outputs along the way.

2 min readRead
Technical

Gaussian Processes

A Gaussian Process is a flexible, nonparametric way to model functions that comes with built-in uncertainty estimates.

2 min readRead
Technical

Q-Learning

Q-Learning is a reinforcement learning algorithm that teaches an agent which actions pay off best by gradually learning the value of each move through trial…

2 min readRead
Technical

Actor-Critic Methods

Actor-Critic methods combine two learners: an 'actor' that chooses actions and a 'critic' that judges how good those actions were.

2 min readRead
Technical

Monte Carlo Tree Search

Monte Carlo Tree Search (MCTS) is a planning algorithm that decides the best move by selectively building a search tree and simulating many possible futures.

2 min readRead
Technical

Adam and Adaptive Optimizers

Adam is the workhorse optimizer behind most modern neural networks, automatically tuning a separate learning rate for every parameter.

2 min readRead
Technical

Learning Rate Scheduling

A learning rate schedule changes the step size during training instead of holding it fixed.

2 min readRead
Technical

Layer Normalization

Layer normalization stabilizes training by rescaling the activations within each individual example so they have zero mean and unit variance.

2 min readRead

Finished reading? Prove it.

Check what you learned with topic quizzes, then explore our structured courses and current certification requirements. Core guides remain free to read.