While prompt engineering concerns the wording of the instruction, context engineering is about selecting and arranging all the information the model sees. This includes relevant documents, conversation history, tool descriptions, and examples, each as compact as possible. The goal is to use the context window optimally without overloading it with irrelevant material. Good context engineering is crucial for capable agents and RAG systems.
Context Engineering
Context engineering is the practice of supplying an AI model with exactly the right information, tools, and examples in the context window. It extends prompt engineering with deliberate control of the entire context.