Part 1: Getting started with LLMs
This opening part lays the foundation for the rest of the book. We’ll explore the “why” and “how” of building applications powered by large language models—what they do well, where they struggle, and why frameworks like LangChain, LangGraph, and LangSmith are essential for creating reliable, real-world systems. Along the way, you’ll discover the main architectural patterns—engines, chatbots, and agents—and learn the core techniques that make them work, including prompt engineering and Retrieval-Augmented Generation (RAG).
You’ll also focus on one of the most important everyday skills in AI development: crafting and executing prompts. We’ll look at how to design prompts for different kinds of tasks, improve them with one-shot and few-shot examples, and automate the entire process with LangChain’s prompt templates and the OpenAI API. By the end of this part, you’ll be ready to move beyond experimentation and start building purposeful, dependable LLM-powered applications.