Thoughts on AI, building systems, and lessons from the trenches.
My most expensive API requests ever are an acknowledgment, a menu choice, and a parade of good mornings. Receipts from 12,992 real Claude Code requests: the 60-minute cache cliff, the subagent meter, and why your bill tracks what the harness re-establishes, not what you type.
Read →Prompt caching is the single biggest cost lever for LLM agents. But it doesn't cache your prompt. Here's what it actually caches, why prefixes must match exactly, and the rules that turn a $4.50 agent run into $0.62.
Read →AI made optimizing your own workflow nearly free. The bottleneck moved from whether it's worth it to whether you even notice. Four levers (Connect, Encode, Teach, Parallelize), each with a tell you can catch yourself in.
Read →Every Claude Code user is running without LSP. That means 30-60s grep searches instead of 50ms precise answers. A deep dive into enabling it: setup, real performance data, and undocumented discoveries.
Read →Hooks are Claude Code's most underrated feature. From the event logger to safety hooks that block dangerous commands and protect secrets, plus a complete guide with ready-to-use code.
Read →