Working notes from inside the studio.

Four Collimer guides still quoted plans we deleted 21 days earlier. The prices were typed into prose, so nothing updated them.

For most $1–50M B2B SaaS companies, an AEO/GEO agency beats a full-time specialist, because AI-engine optimization is a continuous scaffolding problem, not a headcount problem.

On the panel we run against our own site, one run's score carries about 7 points of noise either way, and the score moved by less than one point across two weeks of runs. A two-point change tells us nothing.

One apostrophe moved our scanner's score for a real business from 5/100 to 48/100. The business hadn't changed; our matcher had.

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

Collimer cut three self-serve pricing tiers to one $6,500 guided sprint, reversing a standing rule against ever publishing that number.

Last week's post was a decision: split the Chronicle from a second, buyer-facing content pipeline before there was evidence it would work. This week is the evidence.

The right choice depends on which of three things you are missing: a strategy, a machine, or hands. Most founders at this stage are missing the machine, and none of the three options builds it by default.

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.

A senior owner for your revenue machine at a fraction of a week. The band where renting beats hiring, real price ranges, the five signs you need it now, and when it is the wrong answer.

The same week Nick Bair's name went public, Sandcastle stood up a second writing pipeline next to the Chronicle, built around real bylines and a rule for keeping the two apart.

Collimer's engineer found and fixed five separate, unrelated ways its own AI-visibility score had been quietly wrong, in the same four-day window that shipped seven releases.

A database connection's verify_none setting was a defensible second layer of trust when the transport was an authenticated tunnel. After the database moved to the public internet, the identical setting meant the encryption authenticated nobody, and nothing in the code said so.

Collimer's new pricing page promises unlimited seats. The code enforcing seat limits hasn't caught up yet, and the PR that shipped it said so.

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.

Three point releases shipped in four days, each a coherent batch. The release engineering that made the speed defensible, not reckless, shipped in the same window: zero-downtime deploys, a corrected kill timeout, and a branch-protection rule learned from an actual loss.

A Chrome process wired as a permanent child of the root supervisor exhausted its restart budget when it failed to launch, and the exit cascaded into shutting down scans, dashboards, the API, and background jobs together.

A database-pool fix and a marketing-attribution default were both confidently wrong in the same shape: each cited its own rationale, and nobody had checked that rationale against the actual code.

Collimer's second launch-post cycle made two real decisions: name a real competitor directly instead of gesturing at 'tools in the market,' and recontextualize the original ten-design-partner ambition instead of quietly replacing it.

Building a content skill meant to run inside a client's own repository, without us in the room, taught three disciplines an internal-only tool can skip. The first correction it got wrong taught us the most.

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

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.

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.

The first real week of dripping build logs instead of bursting on Monday also surfaced a portability bug our mining tool had been hiding.

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

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.

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

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.

The homepage now leads with recommendations, not a score. We built EXP-01 to measure the reframe before real traffic arrived.

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.

Collimer went live July 9: one LinkedIn post, 661 impressions, a handful of DMs, two design partners in and a third coming. Plus the numbers we cut before posting, and the competitor one-liner that did not survive our own fact-check.

Collimer's site and app live in separate repos, so we made the product's own pricing config the single source of truth pricing and engine claims sync from.

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

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

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

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.

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.

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.

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.

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.

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.

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.

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.

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.

A scan in a second vertical revealed how SaaS-coded our probes were. The fix made us question whether 'alternatives' is even a real category for local services.

Parallel Claude Code agents built the Collimer MVP end to end in about three days and 67 commits. The pace is only the headline. The point is what kept it from being a pile of code.

An afternoon of Phoenix LiveView produced fourteen connected screens. The clickable mockup is the cheapest discovery tool we have for an AI product.

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.

We wired three LLM providers through one probe runner. The output is a methodology card that shows exactly how each answer was produced.

Every GEO tool ships a beautiful dashboard. We bet the value is the recommendation, and rebuilt Collimer so every rec is shippable as written.