For lighting stores

A lamp is chosen by its shape.

Nobody types “mushroom lamp with a glossy dome”. Lighting shoppers choose on shape and colour, spot lamps in cafés and magazines, and come back for the bulb they forgot. Koral reads your product images and sells each lamp with what it needs.

A store page with See similar on an orange mushroom lamp and a panel of similar lamps

From the right shape to the right bulb.

  1. They can’t name the shape they want.

    01 / 05
    See similar

    See similar on every lamp finds the ones with the same shape, colour and style, all in stock.

    • Listing page
    • Product page
  2. They saw it in a café, a hotel or a magazine.

    02 / 05
    Image search

    Koral finds the lamp in a photo of a room. The shopper taps it or draws around it and gets the closest matches.

    • Search bar
    • Product page
  3. The lamp goes home without a bulb.

    03 / 05
    Complementary products

    The bulb and the add-ons that belong with each lamp, under the buy box, after add to basket and in the basket.

    • Product page
    • Added-to-basket step
    • Basket
  4. The floor lamp has a pendant sister nobody sees.

    04 / 05
    Matching sets

    The pendant, table, floor and wall versions of a design, shown together on every one of them.

    • Product page
  5. Lamps are bought for a room.

    05 / 05
    Shop the look

    Room images made shoppable: the lamp, the side table and the rug, each one a product.

    • Campaign & editorial

Measured on live sites.

Visual discovery
8.0%

Conversion in sessions that used visual discovery, 5× the site average of 1.6%.

+43%

Higher conversion than the site’s other product carousels.

Matching sets, A/B pilot
+35%

More add-to-carts for shoppers who saw a matching set.

+12%

More sales from the baskets those sets created.

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.

Day 1

Feed connected

CSV, JSON or your platform feed. Koral indexes every image, in any language and any category.

Day 2–3

Tag or endpoint wired

Add the tag through GTM, or call the endpoints from your own components. Your design, your markets.

Week 1

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.

FAQ

Frequently asked questions.

Home & living