Shoppers describe the room they are furnishing and get the right fixture back.
Lightopia Ask Cleo
Agent Ready Award Agentic Achievement Award
Ask Frasers Shopping Assistant
A shopping assistant that lifted conversion 25%, taken from a split test to all traffic.
A multi-agent shopping assistant on houseoffraser.co.uk, moved from a 50/50 test to all traffic on a 25% conversion lift.
What the agent does
Routes each shopper question to a specialized sub-agent and assembles the answer, deciding for itself which one to dispatch to.
- Brand
- Frasers Group
- Built by
- Algolia professional services
- Contributed by
- Algolia (Agent Studio and real-time data layer)
- Industry
- Retail, Apparel & Footwear
- Audience
- B2C
01
The problem
Why this exists
A large multi-brand retailer has the product data a shopper needs and no good way to have a conversation about it. Faceted search answers a query the shopper already knows how to phrase, and a shopper who is comparing options, checking a detail, or working out what would suit them is not phrasing a query.
Read more
The usual answer is a replatform, which is why most retailers do not do it. Frasers wanted the conversational layer without rebuilding infrastructure or moving product data.
02
Outcomes
What changes when this is in place
- A 25% conversion lift, publicly announced by Frasers Group, took the assistant from a 50/50 A/B test in early February 2026 to 100% of traffic.
- Shoppers get product recommendations, preference refinement, key product details, price comparisons, and filtered searches through one conversation, and are guided from landing through search and discovery to the product page.
- The scope was originally pre-purchase and purchase. Frasers and Algolia found customers wanted post-purchase support from the same place, so the next phase widens the assistant's remit and the pages it appears on.
Read more
- Beyond Frasers, Algolia reports 120 customers running Agent Studio agents in production, including Orange, Vuori, Dynapar, and Raia Drogasil.
03
How it works
Architecture
Ask Frasers is built entirely on Algolia Agent Studio using a multi-agent orchestrator model. A central orchestrator agent dispatches to specialized sub-agents depending on the query type, so a fitment question and a comparison question do not go through the same logic.
Read more
Agent Studio is the data aggregation layer. It connects to Algolia as the real-time data layer and to Azure AI Foundry for model access. Frasers tested multiple models, including OpenAI and Grok, and kept a flexible arrangement rather than committing to one, which is the specific reason Agent Studio sits between the agent and the models.
The notable part is what did not change. Frasers did not rebuild infrastructure or move product data. The existing Algolia indices were untouched and the product data stayed where it was; the difference is that it is now surfaced through a conversational layer.
Algolia's professional services team built the agent against requirements defined jointly with Frasers.
Ask Frasers sits inside FGPX, Frasers Group's group-wide composable commerce platform delivered with Lab Digital, which won the 2026 Composable Impact Award at MACH X: Toronto.
Open standards used
REST APIs
Tech stack
Algolia Agent StudioAlgolia search indicesAzure AI Foundry
Resources
Next step
Request an intro
Algolia is behind this solution. Ask about lifting conversion on your storefront, 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
- AlgoliaAgent Studio and real-time data layer
Every organization named here has a page listing the rest of its work on the Hub.
Related solutions
100 product descriptions in 30 minutes, against 100 a day by hand.
Matalan Product Description Generation
Add to cart rose nearly tenfold among engaged shoppers, measured against a control group.
Trail Appliances Storefront Assistant
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.
Where this came from
Solution detail is published from the contributor's 2026 Agent Ready submission to the MACH Alliance. Submitter names and contact details are not published. The conversion figure is as publicly announced by Frasers Group.
Status: Live in productionAdded Jul 8, 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.