Press a "Build" chip on any of these to get a full lesson with slides, code and a quiz in under a minute.
74 topics. Open one to watch it work, test yourself, then break it and see what fails.
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Gradient descent and optimisers → Deep learning: the big picture
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Gradient descent and optimisers
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Convolutional networks (CNN)
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Convolutional networks (CNN) → RNNs and LSTMs → Feedforward, RNN and CNN compared
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Training with PyTorch and TensorFlow
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Autoencoders
Learn in this order: Probability and statistics for ML → Discriminative vs generative models
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Generative adversarial networks (GANs)
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Autoencoders → Probability and statistics for ML → Variational autoencoders (VAEs)
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Probability and statistics for ML → Diffusion models
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Encoder-decoder models
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Pretraining objectives: MLM and CLM
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Pretraining objectives: MLM and CLM → BERT and GPT model families
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Build a transformer from scratch
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Tokens and tokenization
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Mixture of experts
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Quantisation and small models
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning → Distillation: small models from big ones
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Context engineering and memory
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning → Quantisation and small models → LoRA and QLoRA
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Hugging Face: models, datasets, Transformers
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning → Quantisation and small models → LoRA and QLoRA → Fine-tuning for summarisation and QA
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning → Quantisation and small models → LoRA and QLoRA → Fast fine-tuning with Unsloth
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Pretraining vs fine-tuning → RLHF and DPO (preference tuning)
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → ChromaDB
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Chunking documents for retrieval
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG)
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → Prompting and structured output → LangChain → Building RAG pipelines with LangChain
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → Hybrid search and reranking
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → Knowledge graphs and GraphRAG
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → LangChain
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → LlamaIndex
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → LangGraph
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling
Learn in this order: Python for AI work → What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → Context engineering and memory → Evals and testing → Agentic AI: agents that plan and act
Learn in this order: Python for AI work → What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → Context engineering and memory → Evals and testing → Agentic AI: agents that plan and act → Multi-agent systems
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → Claude Agent SDK
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → OpenAI Agents SDK
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → Model Context Protocol (MCP)
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Tool calling → Model Context Protocol (MCP) → Python for AI work → Context engineering and memory → Evals and testing → Agentic AI: agents that plan and act → Multi-agent systems → Agent2Agent (A2A) protocol
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Local models with Ollama
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Serving and inference: vLLM, latency, cost
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → Prompting and structured output → Evals and testing → Evaluating RAG: retrieval and answer quality
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Evals and testing
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Guardrails and AI security
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Guardrails and AI security → Tool calling → Securing agents and their tools
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Multimodal models (vision, audio)
Learn in this order: Maths for AI: vectors, matrices, gradients → Neural networks from scratch → RNNs and LSTMs → Attention: self-attention and positional encoding → The transformer architecture → Convolutional networks (CNN) → Vision transformers (ViT)
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Prompting and structured output → Evals and testing → LLMOps and observability
Learn in this order: Maths for AI: vectors, matrices, gradients → Probability and statistics for ML → Linear and logistic regression
Learn in this order: Maths for AI: vectors, matrices, gradients → Probability and statistics for ML → Linear and logistic regression → Decision trees and ensembles
Learn in this order: Maths for AI: vectors, matrices, gradients → Probability and statistics for ML → Linear and logistic regression → Model evaluation: splits, metrics, overfitting
Learn in this order: Maths for AI: vectors, matrices, gradients → Probability and statistics for ML → Linear and logistic regression → Decision trees and ensembles → Model evaluation: splits, metrics, overfitting → Machine learning: the classical toolkit
Learn in this order: Probability and statistics for ML → Maths for AI: vectors, matrices, gradients → Neural networks from scratch → Reinforcement learning
Learn in this order: Probability and statistics for ML → NLP basics: text as data
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Multimodal models (vision, audio) → Prompting and structured output → Tool calling → Speech and voice agents (Whisper)
Learn in this order: What AI is (and isn't) → How LLMs work: tokens, sampling, context → Embeddings and similarity → Vector databases → Chunking documents for retrieval → Retrieval-augmented generation (RAG) → Serving and inference: vLLM, latency, cost → Prompting and structured output → Evals and testing → AI system design: routing, caching and cost
Learn in this order: Python for AI work → Deploying AI apps: containers, CI/CD and releases
Learn in this order: Python for AI work → Backend APIs for AI apps: REST, streaming and auth
Learn in this order: Python for AI work → Backend APIs for AI apps: REST, streaming and auth → Databases, caching and queues for AI backends