Miroglio Group Unleashes Fashion Innovation in Italy with Generative AI on AWS

Overview

Italian fashion company Miroglio Group, which designs and distributes 10 fashion and lifestyle brands across 41 countries, worked with AWS Partner Data Reply to replace its manual product-tagging process with a generative AI-powered tagging system built on Amazon Bedrock using Anthropic's Claude 3.5 Sonnet, combined with a machine learning model trained on the company's historical images. The system analyzes product images and generates accurate technical and editorial tags and descriptions across multiple languages, reaching almost 90 percent accuracy and cutting a task that previously took one month down to about one hour.

The challenge

Miroglio Group used a manual product tagging process that was not only time-consuming but also prone to inconsistencies. The company needed a categorization solution that would maintain accuracy while freeing its teams to focus on creative and high-value tasks.

The solution

Working together, Data Reply and Miroglio Group implemented a generative AI–powered product tagging system using Amazon Bedrock, with Anthropic's Claude 3.5 Sonnet foundation model. They also used a machine learning model trained on Miroglio Group's historical images. The automated solution analyzes product images and information using Amazon Bedrock to generate accurate tags and descriptions (technical and editorial) across multiple languages.

Reported business value

The new system achieves almost 90 percent accuracy in product tagging. Tasks that previously took 1 month can now be completed in approximately 1 hour, freeing staff to focus on more creative and strategic initiatives.