Tapestry Transforms Enterprise Knowledge Management Using Generative AI on AWS

Overview

Tapestry, the luxury fashion retailer behind Coach, Kate Spade New York and Stuart Weitzman, built an enterprise-wide knowledge management chatbot using generative AI on AWS, powered by Amazon Bedrock with Amazon Titan foundation models and the Claude 3 Haiku large language model. Built, tested and deployed in 4 months, the solution is used by roughly 300 employees across six teams, reducing the time employees spend searching for answers and the burden on subject matter experts.

The challenge

With business units spread across multiple continents, Tapestry's organizational knowledge was siloed, making it time-consuming for employees to quickly access critical information and standard operating procedures.

The solution

Tapestry used generative AI on AWS to build an enterprise-wide knowledge management solution, built, tested, and deployed in 4 months, that helps employees access and query company information through an intuitive chatbot interface. The solution uses Amazon Titan foundation models in Amazon Bedrock alongside the Claude 3 Haiku large language model to process natural language queries and deliver precise, contextual responses from the company's knowledge base, with single sign-on authentication to prevent unauthorized access and a knowledge base that updates automatically as new information is added.

Reported business value

The centralized solution is used by six different teams comprising approximately 300 people, and has reduced the time employees spend searching for answers -- they can now find information through a single interface rather than searching across multiple documents, portals, and sites. It has also decreased the burden on subject matter experts who previously fielded repetitive questions, and empowers new hires and employees transitioning teams to get up to speed without relying on colleagues.