Fully automated 7-agent independent website outsourcing system based on Claude Code
A solo operator uses Claude Sonnet 4.6 to build a 7-agent automation system that automatically scans Google Maps for small businesses lacking websites, handling diagnosis, landing pages, videos, and personalized outreach in one go, serving 47 small businesses per month and generating profit.
X (Twitter)@FarhanBuildsAI28likes
Claude Sonnet 4.6Claude Code RouterGoogle MapsLovableHiggsfieldCalendlyMCP servers
Added 2026-10-31 · originally published 2026-10-30
Steps
- 1Configure the orchestrator in the local file system (such as /Users/dev/maps-agency) and Claude Code Router, connecting 1 API key.
- 2Deploy the Scout agent: iterate through Google Maps in the specified city, filtering for high-rated small businesses older than 5 years with fewer than 50 reviews and no website or a website stuck in 2014.
- 3Deploy the Diagnoser agent: generate a 50-word diagnosis, core angle, industry tone, and a cold start message under 70 words for each lead.
- 4Deploy the Builder agent: generate landing page mockups in Lovable via MCP daily for the top 5 highest-quality leads.
- 5Deploy the Filmer agent: extract mockup screenshots and render a 10-second 1080x1920 vertical video via Higgsfield.
- 6Deploy the Pitcher and Checker agents: send personalized messages across multiple channels, filtering out AI hallmarks and buzzwords via evals; simultaneously deploy the Mobile agent on the iPhone to handle positive replies in real time and book Zoom meetings via Calendly.
Ideas for Chinese platforms
Local service customer acquisition transferable to domestic ecosystems: use multi-agent automation to filter target merchants, generate local lifestyle store-visit videos and direct message copy, achieving fully automated lead collection and initial outreach.
Copy-ready prompt
You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes. sub-agents: - Scout (walks through Google Maps in [target city], looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings) - Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words) - Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap) - Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom) - Pitcher (sends a personalized cold message through the right channel for the niche: email, SMS, IG DM, or LinkedIn) - Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending) - Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go). You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds [$3,000] or the reply rate in a niche for the day drops below [12%].
#AI Agent#Claude Code#Automated Marketing#Indie Hacker
Related use cases
Summarized by AI from the original source - refer to the original post for details. Copyright belongs to the original author.