E-CTRL
AI-powered Amazon audit tool that converts sellers into customers
100+ weekly audits | 83% email open rate | 12% consultation bookings
Executive Summary
A comprehensive overview of the problem, solution, and business model.
The Problem
Amazon sellers in the UK/EU market needed a way to prove their listing potential before investing in expensive consultations. Existing audit tools were either too expensive or didn't provide actionable insights for the UK/EU marketplace.
The Solution
Built a dual-path AI-powered audit system that provides free, valuable insights to Amazon sellers while capturing qualified leads for consultation bookings. The system handles both existing ASIN audits and new product readiness assessments.
Business Model
Free tool → Email capture → PDF reports → Consultation bookings. The system generates qualified leads by providing genuine value upfront, then converts them through professional deliverables and strategic follow-up.
Technical Architecture
A comprehensive overview of the technologies and tools used to build this solution.
Frontend
Next.js 14
App Router for optimal performance and SEO
TypeScript
Strict mode for type safety and better DX
Tailwind CSS
Custom design system with 8pt grid
Framer Motion
Smooth animations and micro-interactions
Backend
API Routes
3 main endpoints: /api/preview, /api/report, /api/email
OpenAI GPT-4
AI analysis and personalized recommendations
Supabase
PostgreSQL database with rate limiting functions
Resend
Email service with PDF attachments and tracking
Integrations
Amazon Scraper
Custom regex-based UK marketplace scraper
IDQ Evaluator
8-point binary scoring system for listing quality
PDF Generation
jsPDF for professional audit reports
Rate Limiting
PostgreSQL functions prevent abuse
Development Timeline
A detailed breakdown of the development process, from concept to launch.
Week 1
MVP: Basic ASIN audit with OpenAI integration
Week 2
Enhanced: New seller path and IDQ scoring system
Week 3
Polish: PDF generation, email automation, access control
Week 4
Launch: Rate limiting, error handling, performance optimization
Results & Metrics
Measurable outcomes that demonstrate the success and impact of this project.
Development
Performance
Business Impact
Lessons Learned
Insights gained from building this project and recommendations for future development.
What Worked Well
- Regex-based scraping was more reliable than AI scraping for Amazon data
- Dual-path system addressed different seller needs effectively
- Guest/account split created natural upgrade incentive
- PDF reports significantly increased perceived value
Future Improvements
- Implement rate limiting from day 1 to prevent abuse
- Add more comprehensive error handling for edge cases
- Include competitor analysis features for account users
- Build Chrome extension for instant audits
Unexpected Insights
- Email deliverability required more setup than expected
- PDF generation in serverless environment had encoding challenges
- Amazon's anti-scraping measures were less aggressive than anticipated
- Users preferred binary scoring over 10-point scales