Keep the sale when the size is gone.
Shoes sell out one size at a time, white sneakers all look alike in a text search, and the care kit that belongs with a new pair rarely makes it into the basket. Koral works from your product images and feed to fix all three.
From the size grid to the shoe box.
-
The size they need is gone.
01 / 05Similar in the same sizeA button on the sold-out size shows similar pairs in stock in that size. It filters on whatever size values your feed uses.
- Product page
- Sold-out sizes
-
The care kit never makes it to the basket.
02 / 05Complementary productsCare products, laces and socks that belong with the pair: under the buy box, after add to basket and in the dispatch mail, with a reminder when the care runs low.
- Product page
- Added-to-basket step
- Basket
- Mail flow
-
They saw the shoes on someone in the street.
03 / 05Image searchKoral finds the shoes in a street photo or a screenshot. The shopper taps them, or draws around them, and the rest of the photo is ignored.
- Search bar
- Listing page
-
“White leather sneaker” returns hundreds of pairs.
04 / 05See similarSee similar matches on shape, colour and style, read from the product images, not on shared keywords.
- Listing page
- Product page
-
Shoppers compare pairs before they choose.
05 / 05Related productsA row of the closest visual alternatives on the product page, always in stock.
- Product page
Measured on live sites.
Conversion in sessions that used visual discovery, 5× the site average of 1.6%.
Higher conversion than the site’s other product carousels.
From the clients’ own analytics, A/B-split where possible.
Implementation: this is all it takes.
No model to train, no tagging, no CMS work. The product feed is the only input; the rest is a tag or an endpoint.
Feed connected
CSV, JSON or your platform feed. Koral indexes every image, in any language and any category.
Tag or endpoint wired
Add the tag through GTM, or call the endpoints from your own components. Your design, your markets.
Live and measured
Pilot on one category, A/B-split, with events in your analytics. Then roll out market by market.
99.9% uptime SLA. The script is served from a global CDN; requests are processed in the EU. Koral keeps nothing from shoppers: photos and data are used for the request and not stored. A data processing agreement (DPA) comes with every contract.
Frequently asked questions.
It filters on whatever size values your feed uses, so shoppers see the sizes you actually sell.
No. Every basket line is a seed, and the suggestions are filtered against what the shopper already has.
Yes. Merchandisers see every generated set in the dashboard, and a rules engine covers categories, price bands, stock, margins and brands.