Arcs · active
The Unattended Studio
July 2026 – ongoing
Founding 100 Days ended with the studio finished building itself. This arc is what happened next: the machinery it built kept reporting success while quietly doing nothing, and the work of the season is finding out which parts can actually be trusted to run unattended.
Ending question
Can a studio run on machinery it built itself, without someone watching it every day?
This arc closes when this question is answered honestly. Until then, every post in it is one step toward the answer.
Posts in this arc (13)
- 01
A small AI-native software studio scales by building loops that collaborators can run, not by adding headcount. The unit that compounds is the loop.
- 02
We built the agent-native studio workflow behind our operating plan and scoreboard before hiring anyone, so progress gets measured, not guessed.
- 03
Our GEO crawler signal read zero for two reasons, and both were bugs in our own instrumentation, not a lack of real crawlers.
- 04
Two days before launch we fact-checked our own site and found real mistakes, including 126 stray instances of a habit we ban on our own team.
- 05
Collimer had no working weekly draft loop, so we gave it the same pitch-to-publish rhythm as this site and committed to two posts a week.
- 06
We rebuilt sandcastlelabs.ai on a new brand system, then audited it the same day and caught a leftover internal codename still live.
- 07
A low-token SEO audit of two days-old sites found a 3-hop redirect, a dateless sitemap, a thin page, and short guide descriptions.
- 08
The chronicle's own pipeline learned to rank stories by archetype and scale build-log volume to how eventful the week actually was.
- 09
The first real week of dripping build logs instead of bursting on Monday also surfaced a portability bug our mining tool had been hiding.
- 10
A daily rebuild, a scheduled workflow, and an agent all reported success last week while producing nothing at all. Each one behaved exactly as documented.
- 11
Building faster with AI agents means more of the output ships unverified by default. Three catches in one week show what checking, not prompting, actually buys you.
- 12
Our pitch machine produced a correct artifact in the wrong shape, which meant it failed at the only job that mattered: surviving a handoff between two people.
- 13
We moved the studio's operating scorecard onto a Neon database and a scheduled tick, and a traffic anomaly proved why that mattered.