AI Email Agent for a Trailer Parts E-Commerce Business
Built an AI-powered email agent that automatically labels, drafts, and processes customer emails for TrailerPlus — a Dutch trailer parts e-commerce business. From manual inbox management to automated responses with product knowledge.
About TrailerPlus
Dutch e-commerce business selling trailer parts, accessories, and technical components
Dennis runs TrailerPlus mostly by himself — selling trailer parts, axles, brakes, tires, and accessories online. The business is growing, but so is the inbox. Product questions, order status requests, invoices, marketing emails, contact form submissions — all landing in one Gmail inbox. Every email needed manual reading, labeling, and a response. With hundreds of products and technical specifications, writing accurate replies was eating hours out of every day.
The Challenge
TrailerPlus was drowning in email. Every customer question about brake adjustments, tire compatibility, axle specifications, or order status required Dennis to manually read the email, look up the right product information, and write a response. Marketing emails, payment confirmations, and contact form submissions all mixed together in one inbox with no automatic sorting. The volume was growing faster than Dennis could handle alone, and hiring someone just to answer emails didn't make financial sense for a business this size.
What I Built
I built an AI email agent on n8n that connects to the TrailerPlus Gmail inbox. When an email arrives, the agent reads it, classifies it (product question, order status, payment, marketing), and drafts a response using a knowledge base of product information, technical guides, and company policies. For digital invoices, it processes them automatically. For product questions, it pulls from PDF guides, product pages, and the TrailerPlus catalog to write accurate, technical responses. Dennis reviews the drafts and sends — turning a 15-minute email into a 30-second review.
Automatic Email Classification
Reads incoming emails and labels them by type: product questions, order status, payments, marketing, contact form submissions. No manual sorting needed.
Product Knowledge Base
Trained on TrailerPlus product catalog, PDF guides (brake adjustment, damper overview, tire selection), and product pages. Gives accurate, technical answers.
Draft Response Generation
Generates ready-to-send email responses for customer questions. Dennis reviews and sends — no writing from scratch.
Digital Invoice Automation
Processes digital invoices automatically. Dennis still monitors but trusts the system to handle them correctly.
Contact Form Processing
Handles website contact form submissions, extracting customer details and generating appropriate responses.
Google Ads Alerting
Automated monitoring and alerting system connected to Google Ads via MCC access, sending alerts to Google Sheets for performance tracking.
What This Unlocks
Time and cost spent on repetitive work, before and after.
| Task | Manual | With TrailerPlus | |
|---|---|---|---|
| Reading & labeling emails | Manual, every email | Automatic | |
| Drafting product responses | 10-15 min per email | 30 sec review | |
| Invoice processing | Manual review | Automated | |
| Order status replies | 5-10 min lookup | Auto-drafted |
Reading & labeling emails
Drafting product responses
Invoice processing
Order status replies
Hours saved per day on email alone — time Dennis now spends on growing the business instead of managing an inbox
The Solution
I started with the highest-impact problem: the inbox. Built a V1 email agent on n8n that connects to Gmail, classifies every incoming email, and drafts responses using a knowledge base I built from TrailerPlus product pages, PDF guides, and catalog data. The system handles the full range — technical product questions about axles and brakes, order status inquiries, invoice processing, and filtering out marketing noise. It worked well enough that Dennis invested in a V2: a migration from n8n to the Claude Agent SDK with a proper web dashboard for email management and knowledge base maintenance. That's the sign of a system that actually works — the client wants more of it.
Delivered as a working n8n automation connected to Gmail, with a product knowledge base built from TrailerPlus documentation. The system was live and processing emails within days. Ongoing improvements include expanding the knowledge base with new product guides and preparing the V2 migration to Claude Agent SDK for more advanced capabilities.
- Live email processing within days of starting
- Knowledge base built from product pages, PDFs, and catalog data
- Automatic email classification — no manual labeling
- Draft responses for technical product questions
- Digital invoice automation
- V2 migration planned to Claude Agent SDK with web dashboard
Results
Related Reading
What I Learned Building 30+ AI Agents for Marketing Teams in One Year
More about mindset than technology. FOMO, scaling chaos, and why you're building a hotel — not pitching a tent.
Read →
How to Get Better AI Output: Build a Context System That Actually Works
The more your AI knows, the better it performs. Here's how to build a context system that turns generic AI output into specific, useful results.
Read →
Want results like these?
Whether it's a workshop for your team or a system built from scratch — let's talk about what AI can do for your business.
Get in touch