A practical, accessible guide that shows working software developers how to integrate real AI features into the applications they already build--using JavaScript, Python, APIs, and modern cloud services, without needing a data-science background. Working developers everywhere now use AI tools, but most still struggle to turn prompts and prototypes into reliable software features. Readers learn where AI belongs in an application, how to design around real-world constraints like latency and cost, and how to avoid the brittle prototypes that fail under changing requirements. With clear examples and production-focused patterns, this book helps developers ship AI features that last.

Autorentext

Jacob Orshalick, Jerry M. Reghunadh, and Danny Thompson

Klappentext

Build intelligent applications—no data science degree required.

Your boss is pitching new AI features. Your team is buzzing about MCP servers. Job postings are asking for AI experience with RAG, vector databases, fine-tuning, and agents. You can feel the excitement. You see the potential. You may be wondering how to get started in AI without a data science degree. You’re in the right place.

The Developer’s Guide to AI gives working developers a practical path through the terminology, tools, and implementation patterns that matter. It shows you how to build with AI using the tools you already know: JavaScript, Python, APIs, SDKs, and databases.

By the end of this book, you’ll know how to:

• Call LLM APIs and stream intelligent responses directly to your UI.
• Engineer prompts that produce reliable, production-ready results.
• Build RAG pipelines using vector databases to give AI access to your private data.
• Fine-tune models with LoRA for specialized tasks like classification.
• Deploy AI agents using tool-calling and the Model Context Protocol (MCP) to reason and act inside real workflows.
  LLMs, RAG, LoRA, MCP, embeddings, and agents are not just intimidating buzzwords. They are the building blocks for the next generation of software.

Grab your code editor, bring your engineering instincts, and let’s build what’s next!

Inhalt
Acknowledgments
Preface
Introduction

PART I: GETTING STARTED WITH AI
Chapter 1: Understanding Large Language Models
Chapter 2: Building Your First LLM-Powered Application
Chapter 3: Python Essentials for LLMs and APIs

PART II: PROMPT ENGINEERING
Chapter 4: Fundamentals of Prompt Engineering
Chapter 5: Prompt Engineering Techniques
Chapter 6: Prompt Engineering in Code

PART III: VECTOR DATABASES AND RAG
Chapter 7: Vector Databases in Practice
Chapter 8: Designing a Retrieval-Augmented Generation System

PART IV: ADAPTING MODELS TO REAL-WORLD TASKS
Chapter 9: Why and When to Customize a Model
Chapter 10: Preparing Data for Fine-tuning
Chapter 11: Fine-Tuning Models in Practice

PART V: BUILDING AGENTIC SYSTEMS
Chapter 12: From Workflows to Autonomous Agents
Chapter 13: Building an Autonomous Agent
Chapter 14: Extending Agents with Tools

Afterword
Index