NOW

What's live, recent, and being written.

A snapshot of the build register's current state — the products that are live, the latest entries in the journal, and the newest writing. It updates with the register itself.

In the open

Products currently live.

LIVE · PILOT

ReadySetBind

Turns an insurance quote PDF into a ready-to-sign bind package — the AI reads the fields, a human verifies every one, then it routes to the underwriter. A live pilot.

VIEW CASE STUDY →
LIVE

TariffRefunded

Tariff-refund recovery for small importers. Protest windows close on a fixed legal schedule and the refund pool shrinks 8–10% a month, so the whole product races the clock. Free analysis; broker partnership in progress.

VIEW CASE STUDY →

Latest in the build journal

The three most recent entries. See the full journal →

Recent writing

Field notes from building with AI agents. All posts →

METHODOLOGY

Where your Claude API bill comes from

The subscription version of this cut me off for a week. The pay-as-you-go version doesn't cut you off — it just bills you, and everyone blames the same wrong thing. Your invoice is fully explainable from four numbers on every response.

AUG 2026 · 9 MIN
METHODOLOGY

Why you hit your Claude Code limit

I hit the Claude Max weekly cap two weeks running and blamed my CLAUDE.md. It was the wrong suspect. The real drain is a cache miss — invisible on any per-token chart — and the fix is a habit, not a diet.

AUG 2026 · 9 MIN
METHODOLOGY

A human watching AI isn't oversight

An AI agent told me the emails had all sent. Some never left the building. The return code said success; reality didn't. That gap is the whole problem with 'keep a human in the loop.'

JUN 2026 · 8 MIN
Trust belongs in the schema, not the application.
The operating principle behind every project here. A rule the database enforces can't be forgotten in a hurry. Constraints, denied-by-default access, append-only logs — the controls that hold are the ones the system won't run without.