Glossary · Building
noun
An API feature that stores repeated context, such as long instructions or documents, so later requests that reuse it are faster and cheaper.
In practice
Prompt caching matters for custom tools that send the same long context with many requests, such as a large set of instructions or a reference document. Storing that context means later requests that reuse it are processed faster and cost less. It is a technical optimisation for API builds rather than something people using the Claude apps need to think about.
Yes, for API applications that reuse the same long context across many requests. The repeated part is cheaper and faster to process after it has been cached. Check Anthropic's documentation for current details.
From AI curious to AI capable
Start with an audit. You will know exactly where AI fits, what to do first and what it should give back. Your report looks something like this.
Prepared for
your business
What Claude can really do
Contents
Every opportunity mapped, scored and turned into a costed Claude roadmap.