How my AI agent crew audited 154 small‑business sites and built two 32‑page static sites (with approval gates)

Описание и применение

Автоматизированный процесс аудита 154 малых бизнес‑сайтов и создания двух статических сайтов из 32 страниц с использованием AI‑агентов и строгих контрольных ворот.

Задача

Automating the audit and site‑building process for small businesses while ensuring compliance and quality control.

Результат

Audited 154 businesses, produced 78 mini‑audit PDFs, built two 32‑page static sites, and sent 10 emails while maintaining strict compliance gates.

Рабочий процесс

• 1. Market Researcher selects niche+city and checks domains
• 2. Site Builder receives JSON brief and outputs static site files
• 3. Outreach & Compliance audits prospects and drafts emails
• 4. QA/Verifier re‑checks claims and issues before release
• 5. Approval gates stop any spending, sending, submitting, publishing, or unverified claims

Доказательства

Every agent gets the same block of approval gates pasted into its instructions, ahead of everything else: 1. SPEND: Never buy, subscribe, renew, or enter payment details. 2. SEND: Never send an email, DM, form message, or post. Draft it and queue it. 3. SUBMIT: Never submit an application, signup, or legal agreement. 4. PUBLISH: Never deploy a site, change DNS, or publish content. Build, test, zip, request approval. 5. CLAIMS: Every price, statistic, law, or payout needs a source URL and the date checked.

Источник

The site builder is a Python script: a JSON brief goes in (business type, city, services, service areas, guides, FAQs) and a folder of plain HTML comes out, plus sitemap.xml, ready for Cloudflare Pages.

Источник

Measured on body text only (no header, nav, footer or scripts), that's about 22,100 words for medfordseptic.com and about 20,300 for roanoketreeremoval.com.

Источник

The outreach pipeline: 1. Prospect list: 154 small businesses across 21 cities, 97 in the US and 57 in Australia. 92 had an email address published on their own site.

Источник

Before the first batch, the verifier re‑checked 30 mini‑audits against the live websites. 10 cited a problem the business had already fixed.

Источник