Collimer Build

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.

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

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.

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.

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

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.

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.

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.