Gift shoppers who cannot phrase a keyword search get a curated recommendation out of a conversation instead.
Athena AI Cross-Brand Recommender
Shoppers see relevant products from sister brands without being redirected off the site they are on.
Conversational shopping assistant that surfaces relevant products across a house of brands without redirects.
What the agent does
Interprets a shopper request and recommends across every brand in the group, without handing them off to another site.
- Contributed by
- MACH Alliance (Hub operator)
- Industry
- Retail, Cross-industry
- Audience
- B2C
01
The problem
Why this exists
A house-of-brands retailer with five or 10 distinct storefronts has a discovery problem. A shopper landing on one brand's site never sees a relevant product from a sister brand unless they happen to navigate there. Building a unified discovery layer usually means either redirecting shoppers across domains (which breaks brand context and conversion) or maintaining a brittle cross-product mapping that no one wants to own.
Read more
The opportunity is to let the shopper stay on the brand they came in on, but surface a relevant recommendation from any brand in the portfolio when it actually helps them buy.
02
Outcomes
What this demonstrates
- Cross-brand product recommendations appear in-context, without disrupting the brand the shopper is on.
- The recommendation pipeline runs through Uniform, so personalization rules and content surfaces are editable by marketing, not engineering.
- There is no central product mapping for marketing to maintain. Discovery is driven by signals at request time, not by a brittle cross-reference table.
Read more
- A multi-brand parent can adopt the pattern without rebuilding individual brand storefronts.
03
How it works
Architecture
The reference site runs on Nuxt 4 with TypeScript. It uses Nuxt's Nitro server engine, deployed to Netlify, so the discovery API and the shopper-facing pages share a single deployment unit but serve cleanly through serverless functions.
Read more
Uniform handles personalization and content delivery. The Uniform Nuxt module connects the storefront to Uniform's project for both content fetches and contextual recommendation signals. When a shopper hits a product detail page, Nitro server middleware consults Uniform with the current context (brand, page, signals), receives a ranked set of cross-brand candidates, and renders them inline.
Roadmap items in the repo flag identity provider integration, CRM and CDP data sources, and analytics telemetry as still-open. The reference implementation works end-to-end for discovery rules driven by Uniform; bringing in first-party customer data is the next layer.
Tech stack
Nuxt 4Vue 3TypeScriptUniform (personalization, content delivery)NetlifyNitro
Everyone credited on this solution
Next step
Take the code
This one is published in full. Read it, run it, fork it. Nothing here is behind a conversation.
Request an intro
This one is the MACH Alliance’s own work. Ask about cross-brand discovery without redirects, and the people who built it will 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.
Related solutions
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
A shopping assistant that lifted conversion 25%, taken from a split test to all traffic.
Ask Frasers Shopping Assistant
Verification
Public code
The implementation is published in full, so anything on this page can be checked against the repository. Anything the repository does not show is not established here.
Status: Reference prototypeAdded May 26, 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.