Blog

Thoughts on AI, building systems, and lessons from the trenches.

Anatomy of a $5 “Good Morning”

July 8, 2026 · 13 min read

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 Doesn't Cache Prompts

July 7, 2026 · 12 min 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

You're Slower Than You Think: The 4 Levers of AI-Era Speed

May 19, 2026 · 9 min 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

The 2-Minute Claude Code Upgrade You're Probably Missing: LSP

February 28, 2026 · 13 min 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

Claude Code's Most Underrated Feature: Hooks

January 25, 2026 · 8 min 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