# AI Tutorial - LLM-Friendly Documentation Index

> An Interactive AI Tutorial With Concepts and Lessons Learned. Learn by experimenting with real code — no setup, no dependencies. Every example runs in your browser via StackBlitz with multi-provider support (OpenAI, Gemini, Claude).
> Site: https://aitutorial.dev
> Source: https://github.com/ai-tutorial

## Table of Contents

### Home
- [What Makes This Different](https://aitutorial.dev): Interactive sandbox learning with real code

### Context Engineering & Prompt Design
- [Overview & Learning Objectives](https://aitutorial.dev/prompting/overview)
- [LLM Fundamentals](https://aitutorial.dev/prompting/llm-fundamentals): Tokenization, temperature, context windows, hallucinations
- [Structured Prompt Engineering](https://aitutorial.dev/prompting/structured-prompt-engineering): XML tags, few-shot examples, JSON/XML structured outputs
- [Advanced Techniques](https://aitutorial.dev/prompting/advanced-techniques): Chain-of-Thought, self-consistency, extended thinking, prompt chaining
- [Prompt Optimization](https://aitutorial.dev/prompting/prompt-optimization-and-testing): Evaluation datasets, A/B testing, systematic iteration
- [Prompt Security](https://aitutorial.dev/prompting/prompt-security): Prompt injection, jailbreaking, data exfiltration, PII leakage defenses
- [Model Selection & Cost Optimization](https://aitutorial.dev/prompting/model-selection-and-cost-optimization): Model cascading, prompt caching, TOON format
- [Production Considerations](https://aitutorial.dev/prompting/production-considerations): Versioning, monitoring, deployment checklist
- [Hands-On Exercise](https://aitutorial.dev/prompting/hands-on-exercise): Build a contract summarizer
- [Recap & Resources](https://aitutorial.dev/prompting/recap-and-resources)

### Retrieval Augmented Generation (RAG)
- [Overview & Learning Objectives](https://aitutorial.dev/rag/overview)
- [RAG Fundamentals](https://aitutorial.dev/rag/fundamentals): Core retrieve-augment-generate pattern, production pipeline
- [Search Strategy Selection](https://aitutorial.dev/rag/search-strategy-selection): Lexical (BM25), semantic (vector), hybrid search with RRF
- [Chunking & Metadata Strategies](https://aitutorial.dev/rag/chunking): Fixed-size, semantic, structure-aware chunking, metadata enrichment
- [Working with PDFs](https://aitutorial.dev/rag/working-with-pdfs): Digital and scanned PDF extraction, table parsing
- [Images & Long Documents](https://aitutorial.dev/rag/images-and-long-documents): OCR, image captioning, map-reduce summarization
- [Evaluation & Quality Metrics](https://aitutorial.dev/rag/evaluation-and-quality-metrics): Retrieval metrics, LLM-as-Judge, golden datasets, failure debugging
- [Reranking & Precision Optimization](https://aitutorial.dev/rag/reranking): Two-stage retrieval with cross-encoder reranking
- [Advanced RAG Patterns](https://aitutorial.dev/rag/advanced-rag-patterns): GraphRAG, iterative RAG, agentic RAG, hybrid data RAG
- [Hands-On Exercise](https://aitutorial.dev/rag/hands-on-exercise): Build a production RAG system
- [Recap & Resources](https://aitutorial.dev/rag/recap-and-resources)

### AI Agents
- [Overview & Learning Objectives](https://aitutorial.dev/agents/overview)
- [Introduction to AI Agents](https://aitutorial.dev/agents/intro): LLM vs agent, ReAct loop, LangChain createAgent, weather agent
- [Model Context Protocol (MCP)](https://aitutorial.dev/agents/model-context-protocol): MCP architecture, multi-server design, tool registration, customer support example
- [Agent Memory](https://aitutorial.dev/agents/memory): Working memory (MemorySaver + thread_id), long-term memory, integration patterns
- [Business Rules & Guardrails](https://aitutorial.dev/agents/business-rules-and-guardrails): Deterministic validation, pre/post guardrails, PII detection, jailbreak prevention
- [Tool Selection & Optimization](https://aitutorial.dev/agents/tool-selection-and-optimization): Hierarchical routing, context-based filtering, tool analytics
- [Hands-On Exercise](https://aitutorial.dev/agents/hands-on-exercise): Build a customer support agent
- [Recap & Resources](https://aitutorial.dev/agents/recap-and-resources)

### Coming Soon
- [Coming Soon](https://aitutorial.dev/coming-soon): Multi-Agent Systems, Fine-Tuning, Evaluation & Observability, Data Governance

### About
- [About Us](https://aitutorial.dev/about): Authors, contributing, repositories