Tapestry Transforms Enterprise Knowledge Management Using Generative AI on AWS

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. 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.

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. The solution uses Amazon Titan foundation models in Amazon Bedrock, which provide a breadth of high-performing image, multimodal, and text model choices. 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.

Tapestry’s centralized solution is currently used by six different teams comprising approximately 300 people. The initial rollout was successful and has attracted more teams and personnel to leverage the solution. It has reduced the time employees spend searching for answers. They can now find information quickly through a single interface rather than searching across multiple documents, portals, and sites. The solution has also decreased the burden on subject matter experts who previously fielded repetitive questions. The self-service approach empowers both new hires and veteran employees who are transitioning to different teams to get up to speed without relying on colleagues for basic information.  

With single sign-on authentication, the solution prevents unauthorized access to sensitive data and helps authorized users find what they need. In addition, the knowledge base is automatically updated as new information is added. “Using generative AI on AWS, we are capturing the DNA of our company,” says Aravind Narasimhan, vice president of application technologies at Tapestry. “This solution is going to get people the information that they want much quicker.”

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.

“We want to make the knowledge management solution more intelligent and interactive on the basis of users’ responses,” says Karthigeyan Ramakrishnan, director of applications at Tapestry. “The solution is so good already, but we are looking to enhance it further.”