Introduction
When I started Dream Futures Tech in Pompano Beach, I quickly realized that most small trade businesses in Palm Beach County—plumbers, HVAC technicians, roofers—were missing two things: a simple online way for prospects to request a quote, and a reliable system to keep those leads warm. I built a lightweight website for my own shop and paired it with a home‑hosted automation server that uses Node.js, a tiny SQLite database, and the OpenAI API to send personalized follow‑up emails. Below is a step‑by‑step walk‑through of the pieces I put together, so you can replicate the same workflow for any local service business.
The Business Need
- Capture leads: A single‑page form that works on mobile and desktop.
- Local SEO: Structured data that tells Google the business is a plumber in Pompano Beach.
- Automated nurture: An email that references the specific service the visitor asked about, written by an AI model.
- Low cost: All components run on a Raspberry Pi‑class machine at home, using free tiers of OpenAI and a modest email‑sending service.
Building the Landing Page
I kept the front‑end to plain HTML/CSS so it loads instantly on any device. The form posts to an Express endpoint that stores the data.
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Fast Quote – Pompano Beach Plumbing</title>
<link rel="stylesheet" href="/styles.css" />
</head>
<body>
<h1>Get a Free Quote Today</h1>
<form id="leadForm" method="POST" action="/api/lead">
<label>Name
<input type="text" name="name" required />
</label>
<label>Email
<input type="email" name="email" required />
</label>
<label>Phone
<input type="tel" name="phone" />
</label>
<label>Service Needed
<select name="service" required>
<option value="leak repair">Leak Repair</option>
<option value="water heater install">Water Heater Install</option>
<option value="drain cleaning">Drain Cleaning</option>
</select>
</label>
<button type="submit">Request Quote</button>
</form>
</body>
</html>
The page lives in public/ and is served statically by Express:
const express = require('express');
const app = express();
app.use(express.static('public'));
app.use(express.json());
app.use(express.urlencoded({ extended: true }));
Adding Structured Data for Local SEO
Google likes JSON‑LD that describes the business. I embed it directly in the HTML head. This is a judgment call: the extra markup costs a few bytes but improves local search visibility.
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "Plumber",
"name": "Fast Quote Plumbing",
"url": "https://fastquotepompano.com",
"telephone": "+1-954-555-0123",
"address": {
"@type": "PostalAddress",
"streetAddress": "123 Main St",
"addressLocality": "Pompano Beach",
"addressRegion": "FL",
"postalCode": "33060",
"addressCountry": "US"
},
"geo": {
"@type": "GeoCoordinates",
"latitude": 26.2379,
"longitude": -80.1248
},
"areaServed": "Palm Beach County",
"priceRange": "$$"
}
</script>
Setting Up the Automation Server
All back‑end logic lives on a small Ubuntu VM at home. I chose SQLite because it requires no separate service and is fast enough for a few dozen leads per day.
const sqlite3 = require('sqlite3').verbose();
const db = new sqlite3.Database('./leads.db');
db.run(`CREATE TABLE IF NOT EXISTS leads (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT,
email TEXT,
phone TEXT,
service TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
emailed INTEGER DEFAULT 0
)`);
The POST route validates the payload and inserts a row:
app.post('/api/lead', (req, res) => {
const { name, email, phone, service } = req.body;
if (!name || !email || !service) {
return res.status(400).json({ error: 'Missing required fields' });
}
const stmt = db.prepare('INSERT INTO leads (name,email,phone,service) VALUES (?,?,?,?)');
stmt.run(name, email, phone || '', service, function(err) {
if (err) return res.status(500).json({ error: 'Database error' });
res.json({ success: true, id: this.lastID });
});
});
AI‑Powered Follow‑Up Emails
Instead of a generic “Thanks for contacting us,” I let GPT‑4 draft a short, service‑specific email. The prompt is deliberately simple; more elaborate prompts increase token usage without measurable benefit for this use case.
const { Configuration, OpenAIApi } = require('openai');
const config = new Configuration({ apiKey: process.env.OPENAI_API_KEY });
const openai = new OpenAIApi(config);
async function generateEmail(lead) {
const prompt = `Write a friendly email to a homeowner in Pompano Beach who just requested a quote for ${lead.service}. Mention our company name Fast Quote Plumbing, include a phone number, and ask them to schedule a time. Keep it under 150 words.`;
const response = await openai.createChatCompletion({
model: 'gpt-4o-mini',
messages: [{ role: 'user', content: prompt }],
temperature: 0.6,
max_tokens: 200,
});
return response.data.choices[0].message.content.trim();
}
I use nodemailer with a free SMTP relay (Mailgun’s sandbox domain) to send the email. The code runs in a background job that checks for unsent leads every five minutes.
const nodemailer = require('nodemailer');
const transporter = nodemailer.createTransport({
host: 'smtp.mailgun.org',
port: 587,
auth: {
user: process.env.MG_USER,
pass: process.env.MG_PASS,
},
});
function sendEmail(to, subject, html) {
return transporter.sendMail({
from: 'Fast Quote Plumbing <quotes@fastquotepompano.com>',
to,
subject,
html,
});
}
function processQueue() {
db.all('SELECT * FROM leads WHERE emailed = 0', async (err, rows) => {
if (err) return console.error(err);
for (const lead of rows) {
try {
const body = await generateEmail(lead);
await sendEmail(lead.email, 'Your Free Plumbing Quote', `<p>${body}</p>`);
db.run('UPDATE leads SET emailed = 1 WHERE id = ?', lead.id);
console.log(`Emailed lead #${lead.id}`);
} catch (e) {
console.error('Failed to email lead', lead.id, e);
}
}
});
}
setInterval(processQueue, 5 * 60 * 1000); // every 5 minutes
Deploying and Testing
- Clone the repo on the home server.
-
Create a
.envfile withOPENAI_API_KEY,MG_USER, andMG_PASS. - Run
npm installand thennode index.js. - Verify the form submits by checking the SQLite file (
sqlite3 leads.db "SELECT * FROM leads;"). - Use a tool like MailHog locally to confirm the email payload before sending to real addresses.
I keep the server behind UFW with only ports 80/443 open, and I terminate the Node process with pm2 so it restarts automatically on power loss.
Lessons Learned
- Keep the prompt short – the model produces good results with a single sentence describing the service.
- Rate limits matter – the free OpenAI tier allows 3 requests per minute; batching leads into a single call would be needed for higher volume.
- Local SEO wins – Adding the JSON‑LD snippet moved the business from page 3 to page 1 for “plumber Pompano Beach” in my own tests, even without backlinks.
- Simplicity over perfection – A plain HTML form with server‑side validation beats a fancy React SPA for this audience; trade owners care about reliability, not flash.
Conclusion
By combining a minimal landing page, structured data for local SEO, and an AI‑driven email follow‑up, you can give a Palm Beach County trade business a professional online presence without hiring a full‑time marketer. The whole stack runs on inexpensive hardware you already have at home, and the code is small enough to understand and tweak as the business grows.
I build sites and automations for small businesses at dreamfuturestech.com.
Top comments (0)