Skip to content
All tags

#context

2 posts

How prompt caching shapes Claude Code's speed and bill: prefix matching, invalidation triggers, and hit rate

Claude Code's prompt caching works by exact prefix matching: a cache read bills at roughly 10% of the standard input rate, but switching models, changing effort, enabling fast mode, toggling MCP servers, or denying an entire tool forces the next turn to reprocess everything. The TTL defaults to five minutes; the main conversation and a few helper requests on a subscription get one hour.

RAG Prompt Engineering: How to Design System Prompts and Context

Search found the right documents, but the LLM's answers are still poor — often the problem lies in prompt design. System prompt structure, context formatting, and instruction placement all affect output quality.