Watching your context window like a pot on the stove
You interrupt your own flow to check /context, racing to save your work before compaction eats it. That vigilance is a tax — and you can automate it away.
Stewie Blog — Product truth & behavior specs
Thinking on product truth, behavior specs, and building software that teams can reason about.
Latest posts
Generate technical docs from your codebase — with proof
Generating technical documentation from a codebase is easy now. Trusting it isn't. Evidence-linked claims and human sign-off are the missing steps.
You can't document your way out of comprehension debt
Comprehension debt finally has a name. The popular cure — write more docs — inherits the gap it's meant to close. What actually pays it down.
Compaction amnesia is why you keep re-explaining
Compaction keeps a coding agent running by quietly deleting the why, so you become its memory. What gets lost, why it compounds, and the local-first fix.
LangChain OpenWiki vs Stewie Reflect: docs vs product audit
LangChain OpenWiki validates repo documentation for coding agents. But repo orientation is not the same as evidence-graded product understanding.
Your app works. You still don't understand it.
Your vibe-coded app caught on and now people pay for it — but you can't fully explain it. Build a mental model without reading every line, top-down.
The launch you're not ready for
Your product works. On launch day someone asks what it does at the edges — and you'd have to open the file to answer. That gap is the real launch risk.
Reclaim the product your coding agent built
Vibe-coding got you a working product you can't speak for. Reclaiming it isn't slowing down — it's re-authoring what you shipped, behavior by behavior.
You inherited a codebase you can't read
You own a product you can't explain — acquired, inherited, or vibe-coded with AI. Here's how to read code you didn't really write, behavior by behavior.
Your vibe-coded product is a stranger
You vibe-coded a working product. Users use it. You can't speak for it without reading every line. The product is yours — you just don't know it yet.
Auto-generated specs aren't reliable until you sign off
A 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.
Behaviors, decisions, execution: 3 layers of AI-safe memory
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.
The product engineer era needs product truth
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.
I rebuilt my product from scratch — and didn't lose anything
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.
Generate a behavior spec for your product in 2 minutes
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.
Beyond CLAUDE.md and AGENTS.md: the behavior spec layer
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.
Write your first behavior spec in 15 minutes
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.
The most expensive satisfying feeling in AI-assisted coding
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, PBCs, and test suites are one lifecycle, not rivals
PRDs capture intent. Tests verify assertions. Between them, there's no artifact tracking what the product promises — grounded in code, confirmed by humans.
AI agent context still misses the product layer
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.
What happens to product knowledge when the contract ends?
When an outsourcing engagement wraps up, product knowledge walks out the door. A living behavior spec keeps it in the codebase — not in someone's head.
You shouldn't need an engineer to understand your own product
AI can extract product logic from your codebase. Stewie builds a living behavior spec your whole team can read — no code, no docs, no waiting on engineers.
Five roles, one behavior spec — no code required
Product owners confirm behaviors. BAs clarify logic. QA knows what to protect. New hires onboard fast. Vendors skip reverse-engineering. One shared contract.
You should be able to check what your team actually shipped
Leaders shouldn't need three meetings to verify whether a product decision was implemented correctly. A living behavior spec is the direct line.
Why AI agents keep violating your product rules
Your agent ships code that passes review and still breaks a product promise. It is not a capability gap — it is the product context no rules file gives it.
AGENTS.md, Memory Bank, and PBC solve different problems
Your repo has workflow instructions, session context, and feature specs. None of them answer what the product promises to do. That's the PBC layer.
Vibe coding got you here. Now what?
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.
One file, two audiences
A .pbc.md file opens in VS Code, renders on GitHub, reads like any Markdown doc. Drop it into pbc.stewie.sh and the same file becomes navigable UI.
The PBC spec is live — and it's open source
After hitting the same product knowledge gap across multiple SaaS products, I built an open Markdown spec for capturing what your product promises to do.
Inside the .pbc.md Product Behavior Contract format
A field guide to the .pbc.md format — the structured blocks that make up a Product Behavior Contract: behaviors, triggers, outcomes, and provenance.
What your product does vs. what your team thinks
Product knowledge lives in heads, not docs. Here's why that gap compounds — and what a behavior spec does about it.