A stated goal becomes a finished look, so a shopper who cannot phrase a query still gets a usable answer.
Solution Studio Shopping Greeter
Solution Studio
Kate Spade AI Gift Concierge
Gift shoppers who cannot phrase a keyword search get a curated recommendation out of a conversation instead.
A conversational gift-shopping agent that turns an occasion, a recipient, and a style into a curated set of Kate Spade recommendations.
What the agent does
Holds the gift conversation itself: asks about the occasion, the recipient, and their style, then decides which products to recommend.
- Brand
- Kate Spade
- Built by
- Tapestry's digital teams, building on the Agentic Shopping Assistant on AWS
- Contributed by
- AWS (Agentic Shopping Assistant foundation and the platform it runs on)
- Industry
- Apparel & Footwear, Retail
- Audience
- B2C
01
The problem
Why this exists
Gift buying is the moment in shopping when emotions run high and confidence runs low. A shopper arrives knowing the occasion and the person they are buying for, and not which product to choose. A keyword box assumes the query is already formed, so the intent that carried the shopper to the storefront is lost at the first search. The published announcement cites 53% of shoppers reporting stress during gift purchases.
Read more
The wider driver is ownership of the AI shopping relationship. A retailer either builds its own AI presence or relies on general-purpose answer engines that do not serve its brand or its customers, and the gap widens with every shopper who asks an assistant instead of opening a storefront. Conversational shopping sessions are reported to convert at 3.5 times the rate of traditional keyword search, a figure about conversational shopping in general rather than a Kate Spade measurement.
02
Outcomes
What changes when this is in place
- The assistant reached customers as the first production-ready retail AI assistant built with Amazon Bedrock AgentCore.
- Tapestry skipped the pilot stage and moved straight into a production build, then spent roughly 2.5 months testing before opening it on Apr 13, 2026.
- A Kate Spade gift search now starts with a conversation instead of a guess at keywords, and ends in recommendations shaped by how people shop for gifts.
Read more
- Amazon Bedrock provides observability and evaluations for the assistant in production, so the team can monitor and assess how it performs.
03
How it works
Architecture
The assistant is built on the Agentic Shopping Assistant on AWS, a foundation AWS created with its Generative AI Innovation Center. It packages architecture guidance, starter code, and expert support, and each retailer layers its own data, business rules, and brand voice on top. Kate Spade's layer is the gift-giving logic: the dialogue is designed around how people actually shop for gifts, informed by real shopper behavior, so the exchange reads as a conversation with someone who knows the brand rather than a product search.
Read more
Amazon Bedrock AgentCore is the agent runtime, and Amazon Bedrock provides observability, authentication, and evaluations around it, so the team can monitor and assess a live assistant rather than a test build. Anthropic's Claude Haiku 4.5 is the foundation model, and OpenSearch is part of the foundation. Tapestry skipped the pilot stage and went straight into a production build, then spent roughly 2.5 months testing before opening the assistant to shoppers on Apr 13, 2026.
Tech stack
Agentic Shopping Assistant on AWSAmazon Bedrock AgentCoreAmazon BedrockAnthropic Claude Haiku 4.5OpenSearch
Resources
Next step
Request an intro
AWS is behind this solution. Ask about building a conversational gift-shopping agent, and the MACH Alliance will put you in touch with the person who can answer.
Not ready to talk to anyone? MACH Insider is the Alliance mailing list. New solutions, program openings, and the research behind them, once a month.
Everyone credited on this solution
- AWSAgentic Shopping Assistant foundation and the platform it runs on
Every organization named here has a page listing the rest of its work on the Hub.
Related solutions
A shopping assistant that lifted conversion 25%, taken from a split test to all traffic.
Ask Frasers Shopping Assistant
Shoppers describe the room they are furnishing and get the right fixture back.
Lightopia Ask Cleo
Agent Ready Award Agentic Achievement Award
Verification
Published case study
The detail on this page is drawn from a case study published by the contributor or the MACH Alliance. Any figures on this page are the ones that case study states.
What this page does not establish
- No conversion, revenue, or basket-size figure for Kate Spade is published. The 3.5 times figure describes conversational shopping in general, not this deployment.
- The submission does not say how many shoppers use the concierge, how many conversations it handles, or how recommendations are attributed to it.
- How the agent reads the Kate Spade catalog, ranks its recommendations, and what it declines to answer is not described.
- The testing that preceded launch is described only as roughly 2.5 months. No evaluation results are published.
- The account rests on a single vendor case study. No independent evaluation of the assistant is cited.
Where this came from
Drawn from AWS's customer case study, October 2026, and AWS's announcement of the Agentic Shopping Assistant.
Status: Live in productionAdded Oct 30, 2026A listing is an editorial decision, not a MACH Alliance certification.
Built something worth showing?
Put your agentic solution in front of the enterprise leaders who use the hub to decide what to build next. Submissions are open to MACH Alliance Members, Collaborators, or Ambassadors.