Skip to content
All projects

E-commerce · AI Content Optimization · Human-in-the-loop

E-commerce AI Product Optimizer

Working MVP

An AI-assisted product listing reviewer for Shopify merchants — suggests improved titles, descriptions, SEO fields, tags, and image alt text, with every change requiring human approval and a full audit trail.

Product dashboard showing the mock product catalog and audit summary

Problem

Shopify merchants often have thin product listings — missing SEO titles, meta descriptions, or image alt text — but need AI-suggested improvements they can trust rather than automated rewrites applied without review.

System Design

A dashboard that analyzes the product catalog, suggests improvements to title, description, SEO fields, tags, and alt text, and shows current-vs-suggested side by side for a per-field approve / reject / edit decision.

Workflow Stages

  1. 01Product dashboard
  2. 02Search / status filter
  3. 03AI analysis (title, description, SEO, tags, alt text)
  4. 04Current vs. suggested comparison
  5. 05Human approve / edit / reject per field
  6. 06Audit log

Tools Used

  • Next.js
  • TypeScript
  • Anthropic Claude API
  • Shopify Admin API (read-only)

Safety & Human Review

  • Read-only Shopify access — no mutation path exists in the codebase
  • Human-in-the-loop — every suggestion requires Approve, Reject, or Edit-then-Approve
  • Full audit trail, including which suggestions were edited before approval
  • Safe to demo with zero credentials — deterministic mock fallbacks for both Shopify and Claude

Implementation Evidence

Real screenshots of the working system — collapsed by default so this page stays readable.

What's Working

Demonstrates a working AI-assisted content review workflow with human approval and a full audit trail. No performance numbers are reported because none have been independently verified.

Have a similar workflow to automate?

I'll tell you honestly whether automation is the right fix.