THE CHALLENGE

The Amazon catalog offers a massive selection of items across many product categories, brands, and price points. While this is convenient when a customer is looking for a specific item, it can be overwhelming when a customer seeks to understand their options, make comparisons, or dig into product details. We set out to leverage Amazon’s latest LLM capabilities to offer customers an intuitive way to mine the breadth of Amazon catalog information through a natural-language conversational interface. A special challenge in our process has been the lack of precedent working with nascent technology, determining how to design with capabilities that evolve by the week.

PUBLIC LAUNCH 2024

MY ROLE

  • Design Owner for 7 feature workstreams

  • Strategic Design Leader

  • Oversee 6 UXDs and 3 Conversational Designers

KEY PARTNERS

  • 1 UX Research Team

  • 2 Product Directors

  • 8 Product Managers

  • 2 Data Science Leads

  • 7 Engineering Teams

 

Rufus works as a complement to the Amazon retail app, like a salesperson in a store who’s available at any point in the shopping journey. It engages customers primarily as a bottom sheet over the main pages of the Amazon store, invoked from a persistent icon button.

 

My team owns the core features that assist the shopping journey, including customer onboarding, broad to narrow search CXs, product recommendations, deals discovery, pricing, gifting, and customer service. Working closely with a UX team responsible for shared foundational components, we defined key use cases and flows, and designed new patterns for scenarios and capabilities without precedent. In close partnership with our technical leads, we’ve worked through many debates and iterations to define what kind of content Rufus should surface and how; where and when to provide it; and how proactively to engage customers at any point in the shopping journey.

 

Rufus answers questions about detailed product information, and summarizes customer reviews into an easily glanceable format.

 

Rufus helps customers understand their shopping needs, and compare options.

 

It assists customers with upcoming deliveries and past orders.

We’re continuing to experiment, enhance, and develop new ideas, monitoring both qualitative and quantitative data as we collect feedback and insight from customers. We’ve just gotten started with harnessing the power of generative AI to take Amazon shopping to a new level of convenience, saving customers time and helping them make more informed purchases.