# Visual Product Search AI Case Study: Spotem | DevOps TechLab

> Customers send photos instead of product names; the platform finds visually similar products. How DevOps TechLab built it on AWS.

- Page: https://devopstechlab.com/resources/cases/spotem
- Last updated: 2026-11-14
- Contact: sales@devopstechlab.com · +91 90670 77200 (call or WhatsApp) · Monday to Friday, 10 AM to 7 PM IST
- This is a plain-text copy of the page above for AI tools. The page itself is the reference.

---
1. [Home](https://devopstechlab.com/)
2. [Resources](https://devopstechlab.com/resources/)
3. [Case studies](https://devopstechlab.com/resources/case-studies)
4. Spotem

AI & GenAI AWS Client story

Spotem

# Customers send a photo, sales finds matching products in seconds

DevOps TechLab built a visual product search platform on Amazon Bedrock for Spotem: staff upload a customer’s reference image and get visually similar products from the catalogue within seconds.

By Janak Thakkar, Founder & CEO, DevOps TechLab Corporate gifting 4 min read

Customer’s reference photo

Visually similar products

Illustration

In short

Spotem runs a corporate gifting business whose customers often enquire with photos rather than product names. DevOps TechLab built visual product search on Amazon Bedrock, using Amazon Nova Lite, Titan Multimodal Embeddings and pgvector. Staff now upload a reference image and get visually similar products within seconds, instead of comparing catalogue images by hand.

Official references: [What is Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) · [AWS Well-Architected Framework](https://docs.aws.amazon.com/wellarchitected/latest/framework/welcome.html)

ISO 27001 · SOC 2 · Working with companies across India and abroad from Ahmedabad, in IST

## Executive summary

Spotem’s corporate gifting customers often enquire with photos, screenshots or reference images rather than product names. Staff compared those images against hundreds of catalogue products by hand, and results depended on who was searching. DevOps TechLab built a serverless visual search platform on Amazon Bedrock with Amazon Nova Lite and Titan Multimodal Embeddings, so staff upload the image and receive visually similar products within seconds.

**Client:** Spotem · Corporate gifting

**Business problem:** Photo-based enquiries were matched against hundreds of products by hand.

**What we delivered:** AI visual product search on Amazon Bedrock: image analysis, multimodal embeddings and vector search.

**Engagement:** Discovery, design, build and security, then ongoing optimisation by DevOps TechLab.

**Outcome:** Visually similar products within seconds, without depending on one person’s memory of the catalogue.

## The business challenge

Many of Spotem’s enquiries arrived as images rather than product names. Staff had to compare each image against hundreds of products manually, keyword search could not find visually similar items, and the quality of results depended on who was searching.

### Why it mattered

- **Slow responses to image enquiries**

  Each photo meant a manual search through hundreds of products.
- **Keyword search can’t see**

  Text search could not find products that simply looked like the customer’s reference.
- **Results depended on the person**

  Recommendations relied on individual memory of the catalogue.
- **No appetite for computer vision infrastructure**

  The business wanted image AI without running its own vision models.

## What Spotem set out to achieve

1. Accept a customer’s photo or screenshot as the search.
2. Return visually similar products from the whole catalogue in seconds.
3. Make results consistent, whoever is searching.
4. Use managed AI, with no computer-vision infrastructure to run.
5. Keep images and data secure.

## The solution: visual product search on Amazon Bedrock

Staff upload the customer’s reference image. Amazon Nova Lite analyses it, Titan Multimodal Embeddings turn it into a vector, and vector search finds the closest products in the catalogue.

1. 1 **Upload**

   Staff upload the customer’s image securely
2. 2 **Analyse**

   Amazon Nova Lite analyses the image
3. 3 **Embed**

   Titan Multimodal Embeddings turn it into a vector
4. 4 **Match**

   pgvector with HNSW finds the closest products

### Key design choices

- **Managed image AI**

  Amazon Bedrock with Amazon Nova Lite and Titan Multimodal Embeddings, so there is no computer-vision infrastructure to manage.
- **Fast vector search**

  pgvector with HNSW indexing in Aurora PostgreSQL Serverless v2 finds the closest products quickly.
- **Fully serverless**

  Amazon API Gateway, AWS Lambda and Amazon S3 scale with demand.
- **Lower networking cost**

  VPC endpoints reduce networking cost and keep traffic private.

## Security and governance

Customer images and catalogue data stay inside a private AWS environment, defined entirely as code.

- **Secure image upload**

  Images are uploaded securely to Amazon S3.
- **Least-privilege access**

  AWS IAM roles and AWS Secrets Manager control access and credentials.
- **Private database**

  The database sits on private networking behind Amazon RDS Proxy, with VPC endpoints for AWS services.
- **Infrastructure as code**

  Everything is provisioned with AWS CloudFormation.

## Architecture on AWS

Architecture as built

| AWS service | Role in the solution |
| --- | --- |
| Amazon Bedrock · Amazon Nova Lite | Analyses the customer’s image |
| Amazon Bedrock · Titan Multimodal Embeddings | Turns images and products into comparable vectors |
| Amazon Aurora PostgreSQL Serverless v2 · pgvector (HNSW) | Catalogue data and fast similarity search |
| Amazon API Gateway · AWS Lambda · Amazon S3 | Serverless application and secure image storage |
| AWS IAM · AWS Secrets Manager · Amazon RDS Proxy · VPC endpoints | Access control, secrets and private networking |
| AWS CloudFormation | Infrastructure as code |

## How we delivered

1. 01 **Discover**

   Studied how image-based enquiries arrive and chose Amazon Bedrock with Nova Lite and Titan Multimodal Embeddings.
2. 02 **Design**

   A serverless architecture with vector search on pgvector and HNSW indexing.
3. 03 **Build & secure**

   Secure image upload, AI image analysis, multimodal embeddings and a recommendation service, on private infrastructure.
4. 04 **Optimise**

   Faster search with HNSW, Aurora tuned for workload-based scaling and lower networking cost.

## Business outcomes

Photo enquiries that used to mean a manual catalogue search are now answered with matching products within seconds.

- **Matches within seconds**

  Staff upload a reference image and get visually similar products within seconds.
- **Consistent recommendations**

  Results no longer depend on one person’s memory of the catalogue.
- **Faster replies to customers**

  Image-based enquiries are answered without a manual search.
- **Nothing to host**

  Managed AI on Amazon Bedrock, with no vision models to run.
- **Secure by design**

  Private networking, managed secrets and infrastructure as code.

## What’s next

The same platform can extend to new catalogue categories and vendors. DevOps TechLab continues to tune search speed and cost as Spotem’s catalogue grows.

**About DevOps TechLab**

DevOps TechLab is an AWS Advanced Tier Services Partner with the AWS Generative AI Competency and AWS SMB Competency. We design, build and run cloud and generative AI solutions on AWS for growing businesses, with 265+ cloud environments under management.

### Want AI like this working for your sales team?

Tell us where quotes, searches or proposals slow your team down. We will suggest a small first build on Amazon Bedrock, with the running cost estimated up front.

[Next story · AI & GenAI **HK Infosoft: Semantic product discovery: search the catalogue the way customers talk** Search intent design · 2 min read](https://devopstechlab.com/resources/cases/hk-infosoft)

## More client stories

[AI & GenAI **TNBT Tech: AI agent that finds unusual operational changes and their likely causes**](https://devopstechlab.com/resources/cases/tnbt) [**S3** automatic off-site copies Backup & DR **Dynawiild Engineering: Business data copied to Amazon S3 automatically, for disaster recovery**](https://devopstechlab.com/resources/cases/dynawiild) [Cost & security **SMB on AWS: AWS infrastructure, security and cost optimisation for an SMB workload**](https://devopstechlab.com/resources/cases/smb-optimisation)

Keep exploring

## The work behind this story

- [Service **AI consulting services** Assistants, chatbots and agents on Bedrock, Azure OpenAI or Vertex AI.](https://devopstechlab.com/solutions/generative-ai-data/)
- [Industry **Cloud for retail & e-commerce** Storefronts that hold up on sale day and costs that shrink after peak.](https://devopstechlab.com/industries/retail-ecommerce/)
- [Case study **Semantic product search on AWS** HK Infosoft: search the catalogue the way customers talk.](https://devopstechlab.com/resources/cases/hk-infosoft)
- [Partner **AWS partner in India** Advanced Tier Services Partner with SMB and Generative AI Software Competencies.](https://devopstechlab.com/partners/aws/)

FAQ

## Questions about Spotem's visual product search

**Still have a question?**

Send it with the form below and an engineer will reply.

Ask us

###

Staff upload the customer's image securely. Amazon Nova Lite analyses it, Titan Multimodal Embeddings turn it into a vector, and pgvector with HNSW finds the closest products in the catalogue.

A serverless architecture with API Gateway, Lambda, S3, Aurora PostgreSQL Serverless v2 and Amazon Bedrock. Vector search runs on pgvector with HNSW indexing, and everything is provisioned with CloudFormation.

No. Amazon Bedrock with Amazon Nova Lite and Titan Multimodal Embeddings was chosen so there is no computer-vision infrastructure to manage. The rest of the stack is serverless.

Staff get visually similar products within seconds of uploading a reference image. HNSW indexing speeds up the search, and Aurora is tuned for workload-based scaling.

Image upload is secure, and the platform uses IAM, AWS Secrets Manager, RDS Proxy, private networking and VPC endpoints. VPC endpoints also lower networking cost.

Talk to an engineer

## Start with a 20-minute review. Leave with a plan.

An engineer looks at your current setup, points out what’s costing you money or risk, and tells you what we’d fix first. No sales deck, no obligation to go ahead.

[Sales and general enquiries **sales@devopstechlab.com**](mailto:sales@devopstechlab.com) [Call us **+91 90670 77200**](tel:+919067077200)

Every month you wait, the bill grows, the audit gets harder and the AI project waits another quarter.
