A website built by AI, checked by rules
StudyfinderAI sells pilots to schools and universities, careful public buyers. The site had to explain the product without promising more than it does. I led the relaunch with my co-founder. AI coding agents wrote the code. A claims register and automated tests decided what could ship.
- Business
- StudyfinderAI, co-founded
- My role
- Led the relaunch
- Live since
- 10 August 2026
- See it
- studyfinderai.com
days from first commit to live
What it is: the time from the first line of code to the site going live.
Why it matters
AI coding agents wrote the code, and rules and tests decided what could ship.
commits up to launch
What it is: saved changes to the site's code before launch day.
Why it matters
each task got its own branch and agent, so every change stayed small and easy to check.
Step 02, One task, one branchpages
What it is: the pages of the relaunched site.
Lighthouse accessibility, mobile
What it is: the top score in Google's accessibility check, on a phone, in a lab run.
Why it matters
schools and universities are careful buyers. A site everyone can use is part of the trust. A critical finding fails the build.
GuardrailsLab run on a local production build, 30 August 2026: performance 97 to 99, accessibility 100, SEO 100 on mobile. 0 axe violations on every page at two screen sizes. Initial JavaScript 114,5 kB gzipped, under a 130 kB budget.
How it was built
Eight steps, from rules to launch
Tap a step for the detail. The shape of each marker shows who is in charge.
Step by step
What happened at each step
Guardrails
What keeps it honest
- No unregistered claims. If a sentence isn't in the claims register, it doesn't go live.
- Accessibility is a gate. A critical finding on any page fails the build.
- Speed is a gate. Going over the performance budget fails the build.
- Least access. The contact form can send mail, never read it.
- Fair consent. Reject is as easy as accept.
Built with
Stack, in plain words
- React and TypeScript, built with Vite and styled with Tailwind.
- A 3D scene that loads only when needed.
- Hosting on Vercel, with one small server function for the form.
- Playwright browser tests and axe accessibility scans.
- AI coding agents: Codex and Claude.
What went wrong
What broke, and what I changed
- Two days before launch, the homepage promised more than was true. It described one shared product and one live student journey. Neither existed. Now the first sentence says what the product is and where it runs, and nothing more.
- Contact buttons only opened the visitor's mail app. No confirmation, and no fallback if it failed. I replaced it with a real form backend and a clear success message.
- Wrong claims still got through after launch. Two days after go-live, the high-school page still had wrong lines about fees and the data agreement. I fixed them the same week.
For your business
What you can take from it
- Write the claims before the copy.
Decide what you may promise, with a source for each line. Then AI can write fast without overpromising.
- Let agents ship behind gates.
Automated checks and written risk levels let AI do the work while you keep control of what matters.
- Protect mail when you move a domain.
A website launch should never take your email down. Plan the DNS change around it.
Sources: the project's QA log, claims register, work log and git history, read 2026-11-16. The numbers describe the build, not StudyfinderAI product results.
Next caseThe agent officeContact
Tell me what is stuck
Book 30 minutes on video, or write me a few lines about which AI tools your team uses and where it gets stuck.
consulting@mario-behrends.com