When the Check Is the Bug
Four AI auditors read my service worker twice and agreed it was fine. What they kept rejecting was the checks I'd written to prove it.
// Pillar II — Build
Building and shipping. Sessions where code lands in production, the trade-offs that earned it, and the rules I write so I don't make the same mistake twice.
Four AI auditors read my service worker twice and agreed it was fine. What they kept rejecting was the checks I'd written to prove it.
Four audit rounds caught real bugs. The cheaper fix wasn't more guards — it was removing the option that created the risk.
I thought I had not used my own product for twenty-eight sessions. The database told a different story.
Multi-use tokens defended by policy can be replayed. One-shot tokens defended by structural commit at consume-moment cannot. Cortés knew this in 1519.
Three LLM auditors said the verify script was solid. The fourth auditor ran it. It wasn't.
In 1862 Lincoln signed a law about rail gauges. One hundred and sixty years later it picked my markdown renderer.
Spent a day shipping an auth foundation. Production returned 500 on every signup. The root cause was below where I was looking.
A one-day foundation build where three external AI auditors caught three production-blockers I would have shipped without them.
The truck phone substrate went live end-to-end this morning. Then the actual question landed: how much lock does it need yet?
Twenty-seven days in, the voice-journal back half landed. The harder choice wasn't the code; it was the substrate it sits on.
Some sessions you ship features. Some you ship the pipeline that ships features. Today was the second kind, and the math was clear.
Yesterday's session shipped the platform. Today's session asked what I was actually trying to use it for, and the answer reshaped the whole roadmap.
Cloud foundation shipped tonight. The full breakdown comes tomorrow with a clearer head.
Caught the wrong-product trap at session 16 — pivoted from personal practice substrate to a privacy-first journal competing with Rosebud.
Eight sessions deep on a button that still doesn't work — the question that landed wasn't about the button.
Five-line fix. Sixteen hours of audit. The day the pipeline failed the test it was supposed to apply to the code.
What I thought was a fix turned out to be permission to see the next bug. The recorder worked; the upload behind it didn't.
The site's calendar only showed the current month. The site had no resume. Both fixes started as one artifact each, then turned into three.
The dashboard record button shipped yesterday. Today's verification ran into a sixty-second timeout that wasn't actually connected to anything.
Spent four prompt revisions and five external audits shipping a record button. Caught one real bug, eleven small ones, and a hard rule about when to stop.
A year-old bug caught at intake. Two rounds of internal review approved a flawed prompt. The third pair of eyes saw the timezone bug.
Opened my own dashboard and got a 500. The fix wasn't a bug fix. It was admitting the system was lying to me about what it needed to run.
I shipped an AI mirror today that reads my journals. The part that matters isn't what it knows. It's what it sees.
A week-two shortcut became six-week drift. The migration took an afternoon. The thing it taught took longer.
A vision document said one thing. Three sessions of code shipped another. Nobody on the inside noticed for ten days.
Three rules added to my build pipeline in one session, and the reason each one got run the same afternoon it was written.
S2 cut from 5 tasks to 2. Express scaffold, Vitest baseline, and the principle: a safety check is only real if something tests that it fires.
First Workhorse session: voice journal pipeline, site update, and the patterns that will carry every connector after this.
S2 scaffolded the vault and Workhorse CLI from scratch so every future session has somewhere to write and something to run.
Forge is where the actual work happens — code committed, products shipped, prototypes that survive contact with reality.
Tortoise existed as a plan. Session 1 turned it into a public site with a deploy pipeline.