Context engineering

Context engineering can be defined as the practice of designing systems that provide a Large Language Model (LLM) with all the necessary information to complete a task effectively. It goes beyond prompt engineering since it focuses on building a comprehensive and structured context from various sources like system instructions, external knowledge, memory, tools, and state. The central idea is that the success of a complex LLM-based system depends more on the quality and completeness of the context provided than on the specific wording of the prompt itself.

Tobi Lütke, the CEO of Shopify, coined the term context engineering in a tweet on June 19, 2025. He defined context engineering as the art of providing all the context for the task to be plausibly solvable by the LLM. This novel concept captures the essence of the current evolution of LLM-based systems, inspiring others (like me) to understand and define this emerging engineering discipline. Since then, I've been working on a book entitled Context engineering: the art and science of shaping context-aware AI systems, to be published by Manning in 2026.

This GitHub repository is intended to be a companion resource for this book and a go-to reference for practitioners looking to understand and adopt the context engineering principles.

Warning: This repository is a work in progress, so content and structure may change.

This book aims to provide a strong, general-purpose theoretical foundation for context engineering, supported by hands-on examples. Its table of contents is the following:

Introduction to context engineering
System instructions and user prompts
Retrieval and external knowledge
Tools and memory for AI agents
State and multi-agent systems
Context management and evaluation
Context in AI frameworks
Context engineering in real-world environments
Context engineering through the software development lifecycle
State of the art on context engineering
Appendix A. The AI ecosystem
Appendix B. References and further reading

Each chapter of this book starts by explaining the underlying principles and patterns of each thematic block. Then, the final part of each chapter is devoted to presenting specific examples. This GitHub repository contains all these examples. Moreover, I will include new examples and maintain the existing ones even after the book is published. The goal is to provide an open-source, updated reference for everyone interested in context engineering.

Online tool

This repo also hosts the context-aware prompt builder, an online tool presented in chapter 2 for designing, comparing, and reusing structured prompts across multiple frameworks and AI models.

Resources

Although the concept of context engineering is new, the underlying technologies (LLMs, AI agents, prompt engineering, RAG, MCP, memory management, etc.) have been developed over the years. Nevertheless, summarizing all these converging technologies and tools in a single book is a very challenging task. As you know, nowadays there is more information than ever, and it is very easy to get lost with so many sources. This section summarizes some of the most relevant references and resources I found during my journey to unravel the essence of context engineering.