Skip to main content

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 (25)

  1. 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.

  2. 02

    We built the agent-native studio workflow behind our operating plan and scoreboard before hiring anyone, so progress gets measured, not guessed.

  3. 03

    Our GEO crawler signal read zero for two reasons, and both were bugs in our own instrumentation, not a lack of real crawlers.

  4. 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.

  5. 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.

  6. 06

    We rebuilt sandcastlelabs.ai on a new brand system, then audited it the same day and caught a leftover internal codename still live.

  7. 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.

  8. 08

    The chronicle's own pipeline learned to rank stories by archetype and scale build-log volume to how eventful the week actually was.

  9. 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. 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. 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. 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. 13

    We moved the studio's operating scorecard onto a Neon database and a scheduled tick, and a traffic anomaly proved why that mattered.

  14. 14

    Chase ran our chronicle-and-PR pipeline solo, extended it into new territory, and went back to fix a gap in his own earlier work along the way.

  15. 15

    Collimer shipped twenty releases in three weeks, roughly one every working day. Five of them fixed problems in the score itself, and a correct fix to our own site quietly switched off the pipeline that sends this letter.

  16. 16

    The company letter kept slipping even though nothing was broken. The fix was a script that assembles a fortnight's evidence automatically, so writing it became editing, not staring at a blank page.

  17. 17

    A link-graph sweep of Collimer's 35 guides found 8 orphans, 6 of them the newest, most expensive content on the site.

  18. 18

    Sandcastle Labs discontinued Collimer's self-serve plans and folded its marketing into one brand. The product didn't get smaller. It stopped competing with us for attention.

  19. 19

    An assistant reads every page you ever published, old posts included, plus files a buyer never sees. We audited our own site that way on October 13 and found 12 verified problems, nearly all sentences we wrote ourselves. Here is the checklist, the fixes that took a day, and the one step you cannot skip.

  20. 20

    Five named AI crawlers made 209 fetches on our site in 30 days. What they read, what we changed, and what to check on yours.

  21. 21

    Every build log in our current queue was scored on Collimer's citability rubric before it was scheduled: a floor of 80, a target of 90, at most three passes. What the six signals check, why we hold our own posts to it, what the batch looked like, and the one thing the score cannot see.

  22. 22

    Two studies say engines cite the start of a page and reward numbers with sources. Our content engine turns both into blocking checks: the answer in the first 160 characters, and one quotable stat sentence. Here is the gate, and what it does not prove.

  23. 23

    With us, it starts with a free scan, then a 30-minute call, then a manifesto that opens the 90-day sprint. The scan is proof of the problem. It is not proof that we can fix it, and here is what to ask for instead.

  24. 24

    Engines route on the problem, not the vertical: a local fitness studio went from 0 of 8 to 5 of 8 AI answers in four weeks. In July we still sold to SaaS first. By October our pricing page named four kinds of company. Here is what we can and cannot show about why.

  25. 25

    Our business card is a seven-finger hand that says "Hi five, you did it." Getting AI to draw it took three models, a long descriptive prompt and a designer, because years of fixing extra fingers taught the models to land on five. What changed from 2022 to now, and what the same pull means for how AI describes your business.

Series in this arc