Home » Case Studies » J.Hilburn

50% faster document analysis and decision making due to the integration of a secure and self-hosted AI solution

Client’s result

50% faster document management and analysis
50% more efficient decision-making process

Industry |

Retail Apparel & Fashion

Company size |

51-200 employees

Service | AWS consulting, AWS generative AI services

Location | USA

About the client

J.Hilburn is a custom menswear brand that specializes in personalized clothing. The company was founded in 2007. It focuses on high-quality garments like dress shirts, suits, etc. J.Hilburn emphasizes the use of premium fabrics and craftsmanship. The company offers a bespoke experience through a network of personal stylists. They work with customers to select styles, fits, and fabrics.
The business model revolves around direct-to-consumer sales. This cuts out traditional retail markups. As a result, clients receive a personalized shopping experience and better pricing. by cutting out traditional retail markups. J.Hilburn is also known for commitment to sustainability and ethical manufacturing practices.

Main challenges

Challenge 1

Automate document analysis and management with AI and ensure high accuracy

Challenge 2

Ensure data privacy and security in the new AI-based solution

What we did

Solution 1

A self-hosted AI solution with accurate and efficient document interaction

The client and our team agreed to build an AI-based solution hosted on AWS by the client. It was supposed to automate and optimize the work with documents in a few ways.

Interacting with large volumes of unstructured data requires certain configurations. A system has to facilitate effective document interaction. For this, it needs to be capable of rapid and accurate similarity searches.

To address this, we implemented Qdrant, an open-source vector database. It is designed for high-performance vector similarity search.

Qdrant conducts vector similarity search well due to the following features:

Vector similarity search with Qdrant

Qdrant’s advanced compression techniques and distributed, cloud-native design allow for efficient handling of high-dimensional vectors, enabling quick access to relevant information within documents.

Quick search for relevant information within documents

Our experts deployed a self-hosted embedding model from Hugging Face. Hugging Face provides a variety of pre-trained open-source models. They can be fine-tuned to capture the semantic nuances specific to a domain.

Other advantages of using models from Hugging Face are:

Semantic search and document clustering

It was important to choose the right model. This choice influences the accuracy of information search in a database. Our solution has been correct. It improved the accuracy of tasks like semantic search and document clustering. It also maintained data privacy within the organization’s infrastructure.

Solution 2

Well-configured data privacy and security

IT-Magic’s team used Amazon Bedrock's foundation models. This service prioritizes data privacy and security. Amazon Bedrock never uses customer data for service improvements. It also doesn’t share it with third-party model providers.

The other reasons we chose Bedrock are:

Model catalog in Amazon Bedrock
So, the client didn’t have to create a model from scratch and train it with their own data. There was a simpler solution that could perform as required.
Apart from the advantage for data privacy, Bedrock ensured security in more ways:
As a result, our self-hosted and secure solution was exactly what the client needed. They were completely satisfied with the outcomes of our cooperation.

Key Results and Business Value:

1. Accelerated decision-making processes by enabling secure, AI-driven document analysis by 50%.

2. Enhanced data security and compliance through a self-hosted infrastructure

3. Up to 50% cost efficiency with self-hosted embeddings. It is valid in case of high solution usage (at or above 50% capacity).

Features Delivered:

1. AI-powered document processing and interaction capabilities.

2. Secure, self-hosted environment for handling sensitive data.

3. Robust similarity search functionality for efficient document comparison.

Technologies we used

Open source solution for document analysis

A ready-made open-source solution for document analysis.

Amazon Bedrock

Amazon Bedrock:

Foundation models for AI processing.

Qdrant

Qdrant

Self-hosted vector database for similarity search.

Amazon EKS

Amazon EKS

Managed Kubernetes service for application deployment.

Amazon RDS for PostgreSQL

Amazon RDS for PostgreSQL

Database for storing conversations.

VPN Access

VPN Access

Secured network access to the private infrastructure.

Client’s feedback

“Alex and his team are highly skilled specialists who really know the cloud inside and out. Running code locally on your computer is very different from deploying it. It’s accessible anywhere, while still being secure. I was walked through the whole process based on my use case. The deliverables were completed within the agreed time and budget.”

Yatit Thakker
Sr. Product Manager - AI & ML Innovation

A few words from IT-Magic

We enjoyed working with J.Hilburn. Our team appreciated Yatit’s clear communication and task setting. This contributed a lot to delivering the right results and overall impression about each other. We hope to work together again in the future.
Scroll to Top