The #1 Enterprise AI Growth Partner

Case Study • Visual AI

Finding Luxury SKUs in 60 Seconds—How 9AI Slashed Search Time by 96% for The House of Things

Luxury E-commerce

AI Consultancy + Development

April 2025

Speed

96%

Faster Search

Savings

₹7.5L

Monthly

Visual Search Portal

Drop image or describe furniture

95% Match Accuracy • 0.8 sec

AI Powered

Executive Snapshot

Business Impact at a Glance

Client

The House of Things – Udaipur-based luxury furniture & décor marketplace (30k+ SKUs)

Challenge

Design team spent hours manually matching client references to products; backlog hurt conversions

Services

AI ConsultancyAI DevelopmentAI Agents

Key Results

96% faster

₹7.5L saved

+18% upsell

100% coverage

“The new visual search lets us wow clients in minutes instead of days.”

Head of Design

The House of Things

Challenge & Objectives

Pain Narrative

THOT curates 30k+ designer SKUs, but clients arrive with mood-board images or vague briefs (“mid-century caramel lounge chair”). Designers had to trawl Magento, open dozens of tabs, and still risk missing hidden gems. Average shortlist took 18 minutes, backlog ballooned, and premium clients lost patience—threatening brand equity and revenue.

Legacy Task Bullets

•Manually tag visual cues, guess keywords
•Scroll 100+ product pages per query
•Update option sheets & quotes by hand

KPI Table

Speed product shortlist

18 min → < 1 min

96% faster

Cut labour cost

— → ₹7.5L/mo saved

₹7.5L saved

Boost match accuracy

70% → > 95%

Top-10 match

Raise cross-/upsell rate

+0% → +15%

+18% increase

Solution Overview

AI-Powered Visual Search Platform

Service Pillars Engaged

AI Consultancy

Discovery, SOP mapping, success metrics

AI Development

Multi-modal embedding pipeline, Magento adapters

AI Agents

“Visual Search Bot” orchestrating ingestion → ranking → analytics

How It Works

The platform ingests every SKU from Magento nightly, generating CLIP embeddings that blend product photography with enriched attributes (category, form factor, material, colour, era).

Designers drop a reference image or description; an agent detects objects, fuses text & vision vectors, applies weighted similarity, and returns top-10 matches plus look-alikes for upsell.

Usage, hits, and feedback loop to fine-tune weights are logged in the lead module for continuous improvement.

Platform Interface Preview

Visual Search Portal - THOT

Upload furniture image

ChairsTablesSofas

Search Results95% Match

Search Time: 0.8sMatches: 847Confidence: 95%

Real-time Analytics

180h

Weekly Saved

26%

Upsell Rate

Live System

Architecture & Approach

Implementation Strategy

1Discovery & SOP Design

8 designer interviews, 2 week shadow-work

14 manual steps → consolidated into 4 automated stages

2Deployment & Adoption

Pilot (5 users) → phased rollout (25 users) in 4 weeks

Lunch-&-learn workshops; in-app thumb-up/down training loop

3Technical Build

Input ingestion: Magento web-hooks, nightly CSV diff

Embedding: OpenAI CLIP + custom attribute JSON

Query engine: Vision boundary detection → vector search (PgVector)

Portal: Next.js front-end, role-based auth

Security: VPC-isolated, AES-256 at rest, audit trail to ELK

System Architecture Flow

Designer/Client

Upload image or text query

Visual Search Portal

Next.js responsive interface

Query Engine

CLIP Processing

Object Detector

Vision Analysis

SKU Catalog DB

PostgreSQL + PgVector

Analytics Engine

Usage & Feedback

Process Flow

Client Image

Vision Parser

Similarity Ranker

Designer Shortlist

Real-time

Outcomes & Business Impact

Metric	Pre-9AI	Post-9AI	Δ Impact
Avg. search time per query	18 min	0.8 min	▼ 96% faster
Designer hours on search	200 h/wk	20 h/wk	▼ 90%
Monthly labour spend	₹10L	₹2.5L	▼ ₹7.5L
Client shortlist accuracy	Subjective	95% Top-10 match	▲ Precision
Cross-/upsell conversions	8%	26%	▲ 18 pp
3-yr projected ROI	—	640%	—