Context engineering
Choosing what a model gets to work with. Give it the facts and rules it needs. Leave out clutter that may confuse the task.
The context window is the size of the desk. Bigger models have bigger desks, but every desk has an edge, and things near the edge get less attention.
The fuller definition
Context engineering is the design of what information reaches a model, when it arrives, and how it is organized and maintained across a task.
Go deeper
2,000
8,000
4,000
2,000
A hypothetical 16,000-token budget. Real limits and token accounting depend on the model. Saving a file outside this budget does not mean it is present in the current context, and a passage inside it is not guaranteed equal attention.
A concrete example
A drafting workflow supplies the relevant record passages, current outline, and unresolved issues instead of an entire unfiltered archive.
The distinction that matters
Adding more material can increase noise, cost, and conflicts rather than improve the answer.
Related terms
Context window
How much text the model can hold in mind at once: your question, the documents you added, and the conversation so far. Anything outside it is invisible to the model.
Documents & retrievalRetrieval
Searching a larger set of records for useful parts. Finding a passage does not prove it answers the question.
Prompting & contextMemory
A feature that saves facts between conversations so you do not have to repeat them. It is a saved note, not the model learning.
Where it is taught
Give AI a brief it can actually followSource and further reading
Anthropic · Context engineeringThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.