GenAIWiki
Development

Context engineering

Context engineering is the practice of designing what information, tools, memory, and instructions are supplied to a model at runtime.

Expanded definition

Context engineering expands prompt engineering beyond a single prompt string. It covers retrieval strategy, document ordering, metadata, tool definitions, memory, examples, user profile, system instructions, cacheable prefixes, and context-window budgeting. Good context engineering helps models answer with the right evidence and take the right actions while avoiding stale, irrelevant, private, or adversarial context. It is central to RAG, long-context applications, agents, and enterprise assistants.

Related terms

Explore adjacent ideas in the knowledge graph.

Related

Comparisons, tools, and models that connect to this idea.