AI on every page.
No prompt needed.
Koral builds visual discovery and outfitting into the product pages, images and baskets your shoppers already use - helping them find what they love and discover what goes with it.
Built around your product feed. Available through a simple script or API.
More like this, one tap away.
One small button shows look-alike products from your shop.
8% buy. Site average: 1.6%.
Sessions using See similar, measured over six months.
The pieces that belong together.
Matching pieces shown as one set. Add both in one tap.
The small things that finish the basket.
Care, parts and add-ons that belong with the product, priced small enough to add without thinking.
One piece. A complete look.
Koral builds five outfits around every product, in stock and in the shopper’s size.
Show it on them.
Shoppers see the whole outfit on their own photo or an avatar, before they buy.
Generated once. Shown everywhere.
Each product’s set is made once and shows up wherever it adds value: product page, basket, emails, app and assistant.
400,000+ searches every day.
Reaching 8 million shoppers.
Recognise this from your own day-to-day?
-
E-commerce
Instead of shoppers leaving when a size sells out, or when the search box can’t find what they saw.
With Koral every product page leads on: similar products, search by photo and the pieces that belong with it.
Visual discovery → -
Merchandising
Instead of linking matching pieces and add-ons by hand, product by product.
With Koral the sets are generated from your feed for every product and colour, and you review them and set the rules for what shows where.
Matching sets → -
Marketing & CRM
Instead of campaign images that lead nowhere, and emails that show everyone the same bestsellers.
With Koral campaign images become shoppable, and each product’s set follows the order into the confirmation and dispatch emails.
Bundling & outfitting → -
Tech
Instead of building visual search ourselves: 8–12 months, data-science hires and an image pipeline to maintain.
With Koral it is one script tag or one endpoint on your product feed, live in days, with no model to train.
Build vs buy →
What it does, measured by our clients.
Every number comes from the clients’ own analytics, A/B-split where possible.
Visual discovery
Conversion in sessions using See similar, 5× the site average of 1.6%.
Higher conversion than the site’s other product carousels.
Matching sets
More add-to-carts for shoppers who saw a matching set.
More sales from the baskets those sets created.
See similar & image search
Of tracked conversions in the pilot were linked to Koral features.
Higher conversion when Koral tools were part of the session, compared with the site average.
Method and full figures on request. Ask us →
Two families, one engine.
Visual discovery runs from one script tag. Bundling & outfitting is built by AI agents and served by the API.
Image search Search the catalogue with a photo, then refine in words.
See similar One tap from any product to the ones that look like it.
Similar in the same size Sold out in their size? Show what is in stock in it.
Related products The closest visual alternatives, right on the product page.
Discovery on content Start shopping from any content or campaign image.
Shop the look Campaign and editorial images made shoppable.
Shop similar look The whole look from a model image, piece by piece.
Detail view Go deeper on a product without leaving the widget.
AI agents (MCP) Visual search on your catalogue for AI shopping agents and assistants.
Matching sets The pieces that belong together, for every product.
Complementary products The add-ons that belong with the product, at four moments.
Bundles & Finish the look Complete outfits, or complete rooms, around every product.
AI Stylist Personal looks from the shopper’s own inspiration.
Virtual try-on The full outfit on the shopper’s photo or an avatar. 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.
<!-- one tag, via GTM or the template --> <script src="https://script.koral.nu/dist/index.js?searchId=YOUR_SEARCH_ID&similar=true"></script>
Widgets are included and take your colours, radius and language. Or render your own components on the same data.
POST https://search.koral.nu/api/v1/search/complementary
{ "productId": "YOUR_PRODUCT_ID", "feedId": "YOUR_FEED_ID" }
200 OK
{ "matches": ["231956529", "231955952"] } Sets are generated ahead of time, so the endpoint just serves them, sub-second. Your team renders them where they belong.
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.
The capability without the build.
Compare build and buy →- Build in-house
- 8–12 months (Koral’s estimate)
- Legacy recommendation engines
- Weeks
- Koral
- Days
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.
Simple pricing that grows with you.
Any combination of tools: we set the package together, and every tool can be enabled. The four packages below are starting points. Test first on a free demo page; the pilot is 50% off list prices. Prices excl. VAT.
Essentials
On-site product discovery
Search
Image search + discovery
Baskets
Sets, add-ons and outfits
Complete
Search + Baskets
Frequently asked questions.
Koral adds visual discovery and outfitting to your store: image search, similar products, shoppable content, matching sets, complementary products and complete looks. Most of it is always on, already on the page when the shopper arrives.
Text search depends on the words a shopper knows. Visual search reads the image itself, including colour, shape, style and pattern, and finds the closest matches in your catalogue.
With AI agents that each do one job and check each other’s work. One agent finds candidates in your feed, one verifies each piece, one judges whether it belongs, and one composes the set. Outfits are ranked on quality. Rule-based checks run between the steps, a weaker run never replaces a better stored result, and merchandisers can review every set in the dashboard.
Any platform. Visual discovery is one script tag, added through GTM or your template. Bundling and outfitting are REST endpoints your team calls with a product ID. Your product feed comes in as CSV, JSON or your platform feed.
Essentials starts at €1,100 per month and Search at €2,400, each for one market on web and app. Baskets, with matching sets, complementary products, bundles and AI Stylist, starts at €1,600 for up to 25,000 product updates per month, and Complete, with both, starts at €3,600. These are starting points: any combination of tools is possible, and we set the package together.
Connect your feed on day one, add the script tag or wire the endpoint on day two or three, and run a measured pilot from the first week.
First we build a free demo page on your own catalogue. The pilot is then one month on your own site at 50% off list prices, usually on one category and A/B-split, with events in your own analytics.
Yes. A REST API with sub-second responses, a 99.9% uptime SLA and full documentation. The script is served from a global CDN; requests are processed in the EU. Matching sets and complementary products are generated ahead of time, so the endpoints just serve them.
Fashion, home & interior, electronics, toys, sports, and more. The engine works across e-commerce verticals.
























