// blog

Patterns, not opinions.

Notes on the architecture decisions inside this boilerplate — billing AI by usage, keeping codebases agent-readable, and the plumbing in between.

• July 21, 2026 · 5 min read

  Billing AI products by usage: the credit-ledger pattern

  Why subscriptions fail for AI SaaS, and how a two-table credit ledger meters real token usage safely.

  Read →

• July 21, 2026 · 4 min read

  CLAUDE.md: teaching your codebase to explain itself

  Agents fail by guessing. A single source-of-truth file with rules, maps, and recipes turns guesses into pattern-matching.

  Read →