How Rufus scales conversational shopping experiences to millions of Amazon customers with Amazon Bedrock

Our team at Amazon builds Rufus, an AI-powered shopping assistant which delivers intelligent, conversational experiences to delight our customers.

More than 250 million customers have used Rufus this year. Monthly users are up 140% YoY and interactions are up 210% YoY. Additionally, customers that use Rufus during a shopping journey are 60% more likely to complete a purchase. To make this possible, our team carefully evaluates every decision, aiming to focus on what matters most: building the best agentic shopping assistant experience. By focusing on customer-driven features, Rufus is now smarter, faster, and more useful.

In this post, we’ll share how our adoption of Amazon Bedrock accelerated the evolution of Rufus.

Building a customer-driven architecture

Defining clear use cases are fundamental to shaping both requirements and implementation, and building an AI-powered shopping assistant is no exception. For a shopping assistant like Rufus our use cases align with the kinds ...