Enterprise Knowledge Search
As part of its digital-transformation journey, Tapestry has embraced a bold approach to implementing generative AI across its enterprise. Wanting to start with an internal solution before expanding to public applications, the company identified knowledge management as an ideal starting point that would both streamline operations and demonstrate AI's transformative potential.
Reported impact
Tapestry's knowledge management solution is now being rapidly adopted across the organization. Multiple departments are eager to incorporate their knowledge bases into the new system, and the company is adding new features to enhance the system's capabilities, such as voice interaction.
Tapestry , the global luxury retail company behind iconic brands such as Coach and Kate Spade, spans over 1,400 stores and 18,000 employees worldwide. With business units spread across multiple continents, Tapestry's organizational knowledge was siloed. That made it time-consuming for employees to quickly access critical information and standard operating procedures. To address this challenge, Tapestry used generative artificial intelligence (AI) on Amazon Web Services (AWS) to build an enterprise-wide knowledge management solution that transforms how employees access and interact with company data. In 4 months, Tapestry built, tested, and deployed a knowledge management system that helps employees access and query company information through an intuitive chatbot interface.
In 4 months, Tapestry built, tested, and deployed a knowledge management system that helps employees access and query company information through an intuitive chatbot interface. With access to the Claude 3 Haiku large language model through Amazon Bedrock, the solution can also process natural language queries and deliver precise, contextual responses from the company's knowledge base.
"Using generative AI on AWS, we are capturing the DNA of our company," says Aravind Narasimhan, vice president of application technologies at Tapestry.
It has reduced the time employees spend searching for answers.
Tapestry chose AWS to power this solution because of the advanced capabilities available through services such as Amazon Bedrock , which offers a choice of high-performing foundation models.
The solution uses Amazon Titan foundation models in Amazon Bedrock, which provide a breadth of high-performing image, multimodal, and text model choices.
To address this challenge, Tapestry used generative artificial intelligence (AI) on Amazon Web Services (AWS) to build an enterprise-wide knowledge management solution that transforms how employees access and interact with company data.
With access to the Claude 3 Haiku large language model through Amazon Bedrock, the solution can also process natural language queries and deliver precise, contextual responses from the company's knowledge base.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Jan 8, 2025 Tapestry For luxury retailers, understanding customer preferences and empowering frontline staff can make the difference between a thriving brand and one that falls behind. Tapestry , the parent company of iconic brands like… 1 year Amazon Bedrock · Amazon Transcribe · Amazon Translate 
Google Cloud Sample Archived · Oct 8, 2026 Smyths Toys Smyths Toys needed to handle growing customer-service volume across email, web, and social channels while giving AI agents access to live order, shipping, refund, and product data without slowing or destabilizing core… Resolved more than 300,000 customer emails BigQuery · Gemini Enterprise · Gemini Enterprise Agent Platform AWS Sample Sep 29, 2026 National Library Board As the National Archives of Singapore prepared to release newly declassified records from The Albatross File, the National Library Board needed to broaden public access to historically important archives without… 100K visitors generating 90,000+ questions through the ChatBook in 5 months AWS · Amazon Bedrock · Anthropic foundation models 