PRDs capture intent. Test suites verify assertions. But between those two, there's no artifact that tracks what the product promises to do — grounded in code, confirmed by humans. That's the PBC layer.
AI coding agents now have AGENTS.md, memory banks, harnesses, evals, and monitors. They still lack product context: what the product promises to do and which behaviors must stay true.
AI can now extract product logic from your codebase. Stewie builds a living product contract your whole team can read — no code, no stale docs, no waiting on engineers.
Your coding agent ships correct-looking code that breaks product promises. The problem isn't capability — it's a missing context layer that AGENTS.md and memory banks were never designed to provide.
Your repo has workflow instructions, session context, and feature specs. None of them answer: what does the product promise to do? That's a different layer — and it needs its own artifact.
Shipping fast with AI coding tools is genuinely good. The problem isn't the speed — it's what gets left behind. Product reasoning doesn't survive the vibe.