// THE FIELD GUIDE

LEARN AI

A plain-English encyclopedia of AI engineering — LLMs, RAG, vector databases, agents, fine-tuning and the tools around them. Pick a track. Every page starts from zero and ends deep.

See the whole mapevery topic as one interactive graph

LLM FundamentalsHow large language models actually work — tokens, transformers, context windows, and why they make things up.LLM BasicsTokens & TokenizationTransformers & AttentionHow Text Generation WorksContext Windows & Model MemorySampling, Temperature & Hallucination Prompt EngineeringGetting reliable output from a model using nothing but words — from first prompt to injection defense.Prompting BasicsReasoning TechniquesContext EngineeringPrompt Injection & SecurityPrompt Iteration & Management Working with LLM APIsCalling Claude, GPT, and Gemini from code — streaming, structured outputs, function calling, caching, and the bill.API BasicsProvider GuidesStreaming & Structured OutputsFunction CallingCost, Caching & Rate Limits Embeddings & Vector DatabasesTurning meaning into math — embeddings, similarity search, and every major vector store.Embeddings ExplainedSimilarity Search & IndexingVector Database GuidesVectors in Production Retrieval-Augmented Generation (RAG)Grounding model answers in your own data — chunking, retrieval, reranking, GraphRAG, and evaluation.RAG FundamentalsChunking & IngestionRetrieval & RerankingAdvanced RAG ArchitecturesRAG Evaluation AI AgentsModels that loop, use tools, remember, and act — the agent loop, MCP, memory, multi-agent systems, and computer use.Agent FundamentalsTool Use & Tool DesignModel Context Protocol (MCP)Planning & MemoryMulti-Agent Systems & Computer Use Agent SDKs & FrameworksEvery major way to build an agent — provider SDKs, LangGraph, CrewAI, DSPy, and the case for no framework at all.Choosing a FrameworkProvider Agent SDKsLangChain & LangGraphOrchestration FrameworksLightweight & Typed Frameworks AI Coding & Developer ToolsThe tools that write code with you — Claude Code, Cursor, Copilot, and the workflows that keep agents honest.AI Coding FundamentalsCoding Agents & AssistantsAI Coding Workflows Fine-Tuning & Model CustomizationChanging the weights — SFT, LoRA, QLoRA, RLHF, DPO, distillation, and when not to bother.Fine-Tuning FundamentalsLoRA & Efficient MethodsRLHF & Preference TrainingDistillation & Training Tools Local & Open ModelsRunning models on your own hardware — Ollama, llama.cpp, vLLM, quantization, GGUF, and Hugging Face.Running Models LocallyQuantization & Model FormatsThe Open Model EcosystemInference & Serving Engines Multimodal AIBeyond text — models that see, hear, speak, draw, and film.Vision & Document UnderstandingSpeech & VoiceImage GenerationVideo, Audio & Beyond Production & LLMOpsEverything between a working demo and a system you can put on call — observability, cost, gateways, and guardrails.LLMOps FundamentalsObservability & MonitoringCost & Latency OptimizationGuardrails & ReliabilityTesting & Deployment Evaluation & SafetyMeasuring whether models are good — and keeping them from being bad.Evaluation BasicsLLM-as-a-JudgeBenchmarks & LeaderboardsRed Teaming & JailbreaksAlignment & Safety Basics Building AI AppsFrom first chatbot to hired AI engineer — projects, stack choices, UX patterns, and career path.First ProjectsThe AI App StackAI UX PatternsAI Engineering Career