Every request sends the same 20,000-token system prompt. What would prompt caching save us, and how could it make things worse?

Caching is the cheapest large saving in most AI products, and a single line of personalisation at the top of the prompt can turn it into a 22% cost increase. The arithmetic is short; the layout insight is what scores.

Updated Oct 2026 · Original practice questions with worked answers and teaching rubrics. Our editorial policy explains the sources, review process and limits.