Thinking on product truth, behavior specs, and building software teams can reason about.
Subscribe via RSSA spec extracted from code reads what is there, not what was decided — so placeholders and fallbacks get promoted to intent. Sign-off is the missing step.
Execution memory has tooling. Decision memory is emerging. The behavior layer — what your product promises to do — is the one almost nobody has built yet.
Engineers now make product calls, and the reasoning ends up in Slack threads and PR comments. Here is where to put it so the next person can find it.
AI made the rewrite cheap; recreating years of product decisions from memory did not get cheaper. How to keep the decisions when you throw away the code.
Paste a prompt into Claude or ChatGPT, describe your product module briefly, and get a .pbc.md behavior spec you can view, edit, and commit to your repo.
CLAUDE.md and AGENTS.md tell agents how to work in your repo. They don't tell agents what your product promises. That's a different artifact — the PBC layer.
A step-by-step guide to writing a .pbc.md file for your product's most critical module. Start with plain Markdown; add structured blocks agents can read.
Shipping fast with AI agents feels productive. But the costliest mistake isn't bad code — it's building confidently when nobody wrote down what was decided.
PRDs capture intent. Tests verify assertions. Between them, there's no artifact tracking what the product promises — grounded in code, confirmed by humans.
AI agents have AGENTS.md, memory banks, harnesses, and monitors. They still lack the product context layer — what the product promises and what must hold.
