context engineering

Context engineering is the systematic design and optimization of all the information given to a model at inference time so it can respond reliably. This includes prompts, retrieved documents or memory, tool outputs, metadata, policies, and session state.

Unlike prompt engineering, which focuses on creating instructions, context engineering manages the full payload that occupies the model’s context window.

Typical parts include retrieval and selection of content, chunking and ranking, schema-based formatting, grounding and citations, session history, and integration of tool and API outputs.