Concepts
AI and ML concept explainers with optional interactive visualizations. Follow a learning path or explore individual topics.
Learning Paths
Follow a structured track to build understanding step by step.
AI Foundations
Start here. Build a mental model of how LLMs work, from neural networks to attention.
- 1. What Is a Large Language Model?
- 2. Neural Networks Basics
- 3. Tokenization
- +4 more...
Building RAG Systems
Learn to ground LLMs in external knowledge using retrieval, chunking, and reranking.
- 1. Embeddings & Semantic Search
- 2. Vector Databases & Approximate Nearest Neighbors (ANN)
- 3. Retrieval-Augmented Generation (RAG)
- +3 more...
Customizing Models
From prompt engineering to fine-tuning to building autonomous agents.
- 1. Prompt Engineering Basics
- 2. Fine-Tuning vs Prompt Engineering
- 3. PEFT (LoRA) and Fine-Tuning Recipes
- +3 more...
All Concepts
Beginner
Tokenization
InteractiveLearn how text is split into tokens, why subword tokenizers exist, and how tokenization affects LLM behavior and cost.
What Is a Large Language Model?
Understand what large language models are, how they predict the next token, and why scale matters.
Neural Networks Basics
Learn how neural networks learn patterns through layers, weights, and backpropagation.
Prompt Engineering Basics
Learn the core techniques for writing effective prompts: system messages, few-shot examples, and structured instructions.
Intermediate
Retrieval-Augmented Generation (RAG)
Learn how RAG lets an LLM answer questions using relevant external documents fetched at query time.
Vector Databases & Approximate Nearest Neighbors (ANN)
InteractiveLearn what vector databases store, why nearest-neighbor search must be approximate at scale, and how ANN indexes (like HNSW and IVF) make retrieval fast.
Context Windows & Prompt Budgeting
Build a practical mental model for context limits and how to allocate tokens for better cost, speed, and answer quality.
Decoding & Sampling
Understand how token selection strategies control output quality, diversity, and consistency.
Embeddings & Semantic Search
InteractiveLearn how embeddings turn text into vectors and enable semantic search by finding meaning-based similarity instead of keyword matches.
How Attention Mechanisms Work
InteractiveLearn how attention helps models decide what matters, from query-key-value math to multi-head behavior in modern transformers.
PEFT (LoRA) and Fine-Tuning Recipes
Learn why LoRA-style parameter-efficient tuning is the default in practice and how to choose robust fine-tuning recipes.
Tool Use / Function Calling
Understand how models call external code safely and reliably using structured outputs, validation, and execution boundaries.
Transformer Architecture
Understand how Transformers use attention to process sequences in parallel and power modern LLMs.
Chunking & Indexing Strategies for RAG
Learn how to split documents into retrievable chunks, attach the right metadata, and index content so RAG retrieves the right context reliably.
Fine-Tuning vs Prompt Engineering
Learn when to shape an LLM with prompts versus when to change its behavior with fine-tuning, and the trade-offs of each.
Reranking & Hybrid Retrieval
Learn why two-stage retrieval and keyword+vector fusion improve relevance in real-world RAG systems.
Advanced
Instruction Tuning, RLHF, and DPO
Trace how base models become assistants through supervised instruction tuning and preference optimization methods like RLHF and DPO.
Agents: Planning, Tool Orchestration, and Guardrails
Learn how LLM agents execute multi-step workflows with planning, tool loops, recovery logic, and safety boundaries.