Chunking
Splitting documents into smaller pieces before feeding them to an AI system — so they can be searched, retrieved, and processed more efficiently. Too large a chunk: the AI gets too much irrelevant content with the relevant bit. Too small: the AI loses the surrounding context that makes the relevant bit understandable. Getting chunking right is one of the most practical engineering decisions in building a document-based AI system.
In practice
You want to make your 500-page employee handbook searchable with Claude. You can't paste all 500 pages at once — the context window has limits. Chunking means breaking the handbook into sections, storing each as a separate piece, and retrieving only the relevant sections when a question comes in. It's the preprocessing step that makes large document search work.
Related concepts