Skip to main content

Arcs · closed

Founding 100 Days

May 2026 – late June 2026

The studio's first arc. How Sandcastle Labs got built: the marketing site, the brand voice, the Chronicler pipeline. Drawn primarily from past work, intentionally so. The catalogue needs depth before forward content kicks in.

Ending question

What does an agent-native studio actually look like once it has finished building itself?

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)

  1. 01

    Why a solo studio built an AI-assisted publishing pipeline to share what it is learning, and the human edit gate that keeps it honest.

  2. 02

    What shipped in week one of sandcastlelabs.ai: aurora hero, mobile nav, brand tokens, PostHog A/B. And the parts we left visibly unfinished on purpose.

  3. 03

    Site V1 shipped, the chronicle published its first five posts, and Collimer hit v1.0.0 in a three-day agent-fleet build. The first monthly letter from Sandcastle Labs.

  4. 04

    We taught the publishing pipeline to schedule posts on a static Astro site, mine its own week, and send the newsletter unattended. The goal was never hands-off. It was staying organized.

  5. 05

    Every hero image came out a 1024x1024 square because one API parameter was silently ignored. The bug was small. The lesson about working with AI image generation was not.

  6. 06

    Astro 6, Tailwind v4, Motion, PostHog reverse-proxied through Vercel, and a three-package monorepo underneath. Every piece has one line of defense. Here is what it is.

  7. 07

    Collimer went from a coming-soon page to a full marketing site in five days. Then we deleted a third of it. That was the right call.

  8. 08

    GDPR consent banner built with Vercel's edge IP headers and about 150 lines of Astro middleware. No database, no flag service, no third-party CMP.

  9. 09

    Privacy Policy and Terms for two static marketing sites, built without a lawyer. Here is the threshold we think we hit, and what would change that.

  10. 10

    The content pipeline worked fine for people who live in git. A designer coming on board does not. We built a hub round-trip so non-technical collaborators can revise and publish from Center Pane, with a GitHub Action running Claude headless to do the repo work.

  11. 11

    The first full multi-post week went out end to end: five W25 build logs pitched, drafted, edited, and published with a real author/editor split. The same week, the analytics package broke free of its hard-coded site name and learned to serve both Sandcastle Labs and Collimer.

  12. 12

    We built Lookout, an operator analytics scorecard for both marketing sites. It reads PostHog, assesses what's working with volume-aware confidence, and renders a graph-rich HTML report. Its one design principle: if the numbers are too small to say something real, it says nothing.

  13. 13

    Our GitHub Actions billing lapsed. We replaced it with a pre-push hook. The machine that ships is now the machine that checks.

Series in this arc