AI helped me ship faster. Then I forgot what my product actually does.

Hey IH,

Quick story behind this one.

Earlier this year I shipped an app fast using AI agents — mostly Codex CLI and Claude Code.

A couple of months later I sat down to add a new pricing tier. Should have been an afternoon.

I lost the whole day re-reading my own billing code because the change hinged on a question I couldn't answer:

When someone upgrades mid-cycle, do their new limits kick in right away, or at the next cycle?

I'd wired that logic myself months earlier, and I had no memory of which way I'd chosen.

Then I found six files I didn't remember opening and three integrations I didn't remember choosing.

Everything was technically correct. But I no longer owned it in the way that mattered: I couldn't explain why the product behaved the way it did.

I started calling this comprehension debt.

Not technical debt. Technical debt is code you know is messy.

Comprehension debt is the gap between what your product now does, what you think it does, and what you can actually prove from the repo.

AI agents make this worse in a strange way.

They help you ship faster, but your product starts changing at AI speed while your mental model still grows at human speed.

That's the problem I built Stewie Reflect around.

I wanted a way to read what I shipped in product terms — not reopen every file and reconstruct my own product decisions from scratch.

Stewie Reflect takes a snapshot of a GitHub repo and generates an owner's manual for the product — not a code walkthrough.

The manual is organized around product behavior:

• what the product appears to promise users
• what actually happens in the code
• where auth, billing, limits, integrations, and edge cases live
• which behaviors are clearly supported by evidence
• where the repo is ambiguous or silent

That last part matters most to me. I don't just want prose about my codebase. I want to know what product behaviors I can actually trust.

The shape I was after is closer to a manual than docs.

Docs are referenced.
A manual is read.

Live today as a freemium beta:

• free to generate and preview from your own repo
• you get a real chapter plus a map of every area and finding
• $19 beta unlocks the full manual + Markdown export
• one repo per unlock
• async generation in the background

The format underneath is open source too: Product Behavior Contract, MIT-licensed at github.com/stewie-sh/pbc-spec.

Link: stewie.sh/for/vibe-coders

The sample manual on the landing page was generated from a real codebase. You can read a chapter and click through to the evidence before deciding if it's useful.

What I'm trying to validate:

Is “I can't confidently explain what my AI-built product actually promises and does anymore” a real pain for other builders, or just my own founder/developer anxiety?

And more concretely:

Which part of your own product have you been avoiding because you don't remember designing how it should behave?