AI & automation · solo, agent-assisted

The site-generation pipeline

A business goes in as a map listing and comes out as a deployed website: crawled, scored, designed from its own story, built, deployed and verified.

210

sites generated and deployed

177

live in production

211

designs, no two alike

business verticals

Problem

Thousands of small businesses have a website that is broken, invisible to search, or twelve years old. Nobody is going to tell them, and none of them are going to find me.

What I built

A crawler that scores their existing site across about thirty checks, a generative engine that designs each site from that business's own story, automated Cloudflare deploys, and an operations dashboard.

The AI's role

Agents research each business and write its site. The model never touches the outgoing message: that path is deterministic, because a sentence a stranger reads has to be auditable before it is clever.

Result

568 leads scouted, 210 sites built across 14 verticals, 177 live today.

What it produces

Six of the sites the pipeline generated, deployed and still serving. Every design is one-of-one: the fingerprint registry refuses a new theme that shares more than one of eight design axes with anything already shipped.

Measured on one of them

Lighthouse on restoran-pinot.pages.dev, desktop: accessibility 95, best practices 100, agentic browsing 100. Every generated site ships typed JSON-LD, a sitemap, hreflang pairs, an llms.txt and near-zero client JavaScript.

Stack

Astro
TypeScript
Node
Cloudflare Pages
Cloudflare Workers
D1
Playwright
schema.org / JSON-LD

All work Get in touch →