Long Context
Using a model's ability to process very large amounts of text in one go, instead of breaking it into chunks and searching. Claude can handle up to 200,000 tokens (roughly 150,000 words) in a single context window. For some use cases — analysing a full legal contract, reading an entire codebase, processing a transcript — it's simpler and more accurate to just give Claude the whole document than to build a search system around it.
In practice
You paste all 200 pages of a vendor contract into Claude and ask "what are the termination clauses and auto-renewal terms?" Instead of processing it in chunks and losing coherence, Claude holds the entire document in one session. Long context means you can work with big inputs without breaking them up — especially useful for legal, research, and technical documents.
Related concepts