PromptForge
AI Glossary

Core concepts

Context engineering

Also known as: context management

Definition

Context engineering is the practice of deciding what information enters a model's context window and in what order. As windows grew, choosing what to include became more consequential than wording the instruction.

Prompt engineering focuses on phrasing an instruction. Context engineering focuses on assembling the whole payload: which retrieved documents, how much conversation history, which examples, which tool outputs, and in what sequence.

It matters because context is a scarce, contested resource. Every token spent on a marginally relevant document is a token unavailable for something useful, and models attend unevenly across long contexts. More context is not automatically better context.

The core disciplines are retrieval quality, summarising history rather than replaying it, ordering by relevance rather than chronology, and aggressively pruning anything that does not contribute to the current step.

Related terms

Put this into practice

Understanding the term is step one. Our free courses and tools let you actually use it.