Notes from building for schools: AI that pays for itself in a school building, software that survives a school year, and what a two-sided education marketplace has taught us.https://brilliantsector.com/https://brilliantsector.com/journal/ai-workflow-test/https://brilliantsector.com/journal/ai-workflow-test/Most school AI pilots come unstuck for the same unglamorous reason: everyone agrees to try it before anyone agrees what success would look like, so what gets measured is enthusiasm. Here is the test we run before writing any code.Fri, 12 Jun 2026 00:00:00 GMThttps://brilliantsector.com/journal/multi-tenant-from-day-one/https://brilliantsector.com/journal/multi-tenant-from-day-one/Retrofitting tenancy into a live product is one of the most expensive mistakes in software. Here is why we made the call before the first feature, and what it cost us up front.Thu, 28 May 2026 00:00:00 GMThttps://brilliantsector.com/journal/what-families-struggle-with/https://brilliantsector.com/journal/what-families-struggle-with/Eligibility turns out to be the easy part. We asked Alabama homeschool families what wastes their time, and the answer reshaped the product roadmap.Thu, 14 May 2026 00:00:00 GMThttps://brilliantsector.com/journal/silent-failures/https://brilliantsector.com/journal/silent-failures/An error nobody sees is a bug that ships and then lives in production for months. Here is a short argument for loud, unignorable failure.Thu, 30 Apr 2026 00:00:00 GMThttps://brilliantsector.com/journal/where-we-avoid-ai/https://brilliantsector.com/journal/where-we-avoid-ai/There are three kinds of school work where adding a model reliably makes things slower, riskier, or harder to trust. Here is what we suggest doing with each of them instead.Thu, 16 Apr 2026 00:00:00 GMT