Live Demo

Meet ShopSense

Track shipments in real time, get instant AI-powered refund decisions, and discover products that actually match your taste, not just "people also bought" noise.

#ecom-demo
ShopSense , AI-Powered E-Commerce Intelligence preview

Live Tracking

Unified carrier API aggregation, FedEx, UPS, USPS, DHL normalized into a single real-time timeline with proactive delay alerts

0% fewer WISMO tickets

AI Refund Agent

Understands return policies, product condition, and order history, resolves 80% of refund requests in under 8 minutes

0min avg resolution

Taste Profiling

Builds preference vectors from browsing, purchases, and reviews, then surfaces products with explainable match scores

0% of revenue driven

Happy Customers

Post-purchase experience that actually works, real-time updates, instant resolutions, and recommendations that land

0/ 5 satisfaction
AI Agent 2026

ShopSense , AI-Powered E-Commerce Intelligence

Built an intelligent e-commerce operations platform that gives customers real-time shipment tracking with proactive delay alerts, handles refund requests through an AI agent that actually understands context, and recommends products based on genuine taste profiling, not just "people also bought" noise.

Neural Architecture

Commerce Intelligence Graph

Watch customer signals flow through AI processing layers in real time. Hover nodes to see the data transform.

Browse
Page views, dwell time, scroll depth
Signal: Interest vector [0.8, 0.3, 0.6]
Cart
Add/remove patterns, abandon timing
Signal: Purchase intent 0.72
Returns
Return reason codes, condition scores
Signal: Satisfaction delta −0.35
Reviews
NLP sentiment, feature mentions
Signal: Sentiment +0.82 (audio quality)
Embeddings
384-dim user preference vector
Updated every 50ms during session
Model: all-MiniLM-L6-v2
Intent
Classifier
Multi-label classification
Track | Refund | Recommend | Support
Confidence: 0.94
Context
RAG
Vector search: order history + policies
Top-k=5, reranked by recency
Store: Pinecone (1536 dims)
Taste
Engine
Cosine similarity × recency decay
Category affinity + price sensitivity
Output: Ranked product list
Refund
Agent
Policy compliance check + fraud score
Auto-approve | Manual | Deny
SLA: < 8 minutes
Carrier
Intel
FedEx + UPS + USPS + DHL unified
Proactive delay detection (24h window)
Output: Timeline + ETA
Picks
Personalized recommendations
94% match, Sony WH-1000XM5
91% match, Keychron Q1 Pro
Action
Instant refund approved, $89.99
Card credited in 2-3 business days
Confidence: 0.97
Alert
Delay alert: Order #7291 +1 day
Proactive SMS + email sent
Compensation coupon auto-generated
Learn
Feedback loop → retrain embeddings
A/B test: +12% CTR on recs
Drift detection: monthly recalibration
Customer Signals
AI Processing
Decision Agents
Intelligent Output
Customer Dashboard

Your Orders, Unboxed

Real-time shipment tracking, instant refund status, and personalized recommendations, all in one place.

Shipment Tracker
#ORD-7291Wireless Headphones Pro
OrderedMay 14
ShippedMay 15
In TransitMemphis, TN
DeliveredEst. May 19
#ORD-7288Ergonomic Keyboard
OrderedMay 10
ShippedMay 11
In TransitMay 12
DeliveredMay 13
For You, Based on Your Taste
Studio Monitor Headphones$189, 94% match
You loved: Wireless Headphones Pro
Custom Keycap Set, Retro$45, 91% match
You bought: Ergonomic Keyboard
Ultra-Wide Monitor 34"$429, 87% match
Browsed: Desk Setup category
ShopSense
Online, BrightCart

Hey there! I'm ShopSense, your personal shopping assistant. I can track your orders, handle refunds instantly, and recommend products you'll actually love. What can I do for you?

Commerce Intelligence

Shipment Pulse
842In Transit
97%On Time
12Delayed
#7291 Headphones, Out for Delivery
#7288 Keyboard, Carrier Delay Alert Sent
#7265 USB-C Hub, Delivered
Taste Engine
28%Rev Share
34%Repeat
4.6CSAT
Sony WH-1000XM5, 94% match
Keychron Q1 Pro, 91% match
LG UltraWide 34", 87% match
3 users need re-profiling (stale data)

The Challenge

BrightCart was losing customers to poor post-purchase experience. Shipment tracking was a black hole, customers got a tracking number and nothing else until delivery (or a missed delivery). Refund requests took 5-7 business days because every case went through manual review. And their recommendation engine was the usual "frequently bought together" algorithm that suggested phone cases to someone who bought a laptop. Customers were frustrated, support tickets were piling up at 400+ per day, and repeat purchase rate had dropped to 18%.

The Approach

I designed a three-layer intelligence system. Layer 1: a real-time shipment tracking engine that aggregates carrier APIs (FedEx, UPS, USPS, DHL), normalizes status events into a unified timeline, and sends proactive notifications when delays are detected, before the customer even asks. Layer 2: an AI-powered refund agent built on Claude API that understands return policies, product condition context, and order history to resolve 80% of refund requests instantly with fair, consistent decisions. Layer 3: a taste-profiling recommendation engine that builds customer preference vectors from browsing patterns, purchase history, review sentiment, and explicit preferences, then uses cosine similarity to surface genuinely relevant products with explainable match scores.

Results

--
Support tickets reduced by 62% (from 400+ to ~150/day)
--
Refund resolution time dropped from 5 days to 8 minutes
--
Repeat purchase rate improved from 18% to 34%
--
AI recommendations drove 28% of total revenue
--
Customer satisfaction score improved from 3.2 to 4.6/5
--
Proactive delay alerts reduced "where is my order" tickets by 74%
Interactive Demo

Opens chat panel on this page

Project Details
Client
BrightCart (D2C E-Commerce)
Role
Lead Developer and Business Analyst
Duration
12 weeks
Year
2026
Tech Stack
Claude API Python FastAPI PostgreSQL Redis Carrier APIs Pinecone React WebSockets

Interested in a similar project?

Let's Talk All Projects