Sports and outdoor
Winter jackets that go live late end up on sale.
Cernel reads the specs in supplier files and on brand pages into your filters, so the whole range is live before the weather turns.
Trusted in sports and outdoor
Sound familiar?
Launch products go first. The rest of the range waits offline.
The season has a start date
Products with a launch date jump the queue. The rest of the range waits offline for weeks while someone types in the specs, and gear that misses its weeks ends up discounted.
An automation enriches each product as it arrives, so the whole range is ready, not only the launches.
The numbers sit in prose
Waterproof rating, weight and comfort temperature sit in a description, a PDF spec sheet or the brand's own page. None of it filters, so none of it compares.
Agents read each figure into a field of its own, in fixed units, from your supplier files and the brands' published product pages.
A wrong spec comes back
A guessed temperature rating is a product that fails on the mountain. On bulky gear, a return costs twice.
Technical fields are only filled from a source that states them, and you choose which values a person sees first.
Brand terms do not translate word for word
Model names, sport terms and size charts get mangled when every market is rewritten by hand or run through a generic tool.
Each language gets its own instructions, and model names and sport terms stay exactly as the brand wrote them.
Built for the conditions
Shoppers search for the weather they will be out in.
Nobody types a model code. When the rating, the season and the activity sit in a paragraph, the jacket is a dead end in your filters. Cernel puts each one in a field of its own, so search can answer every word.
Your shopThe shopper searches
3-layer shell jacketJKT SHELL 3L 20K M TEALOur toughest shell yet. 20K HH, fully taped, 3L fabric, pit zips, fits over a helmet. Great for the shoulder seasons.EmptyEmptyEmptyEmptyEmpty
Blank beats wrong
A guessed rating comes back. So Cernel does not guess.
A wrong waterproof rating is worse than an empty one. Technical fields stay empty when no source states them. You choose which values go live automatically and which get a review step; review steps check every value and only ask a person when something fails or needs a decision.
- Waterproof rating Looking for a source
- Breathability Looking for a source
- Insulation Looking for a source
- Activity Looking for a source
Review steps check every value. Only one needs a person.
Example product.
Every market
One size chart from the brand. A size guide in every language you sell in.
Run through a generic tool, model names get translated and sport terms lose their meaning. An agent writes the copy and the size guide in each of your languages, by that language's own rules, and keeps model names and sport terms as they are.
CHEST CM S 88-96 M 96-104 L 104-112Danish
SkaljakkeVandtæt 3-lags skaljakke til vandreture om efteråret.
Størrelsesguide
| Størrelse | Brystvidde |
|---|---|
| S | 88-96 cm |
| M | 96-104 cm |
| L | 104-112 cm |
Copy and size guide synced in four languages
Example product and copy.
How it works
From the brand's spec to your filters. What happens to one season's range.
Cernel works next to the systems you already have. Blue is an agent at work, yellow is your team deciding, green is done.
01Comes in
The range comes in
Products arrive from your PIM or shop as they are created, or in a supplier's file. Rows about the same product match on GTIN, EAN or SKU.
02An agent works
Sorted into categories
Every product is classified, so each kind gets its own fields: waterproof rating on shells, comfort temperature on sleeping bags, drop on running shoes.
03An agent works
One agent per field
Agents read your data, the photos and the brand's published product page, matched by GTIN or SKU. Figures land in fixed units; what no source states stays empty.
04Your team decides
Checked where it matters
You choose which values go live automatically and which get a review step; review steps check every value and only ask a person when something fails or needs a decision.
05Done
Back to your shop
Approved values go back to your PIM or shop in every language you sell in, or out as an export or a Google Shopping feed.
What changes
Every spec is a filter. Your team decides what goes live.
Fields of their own
- ActivityHiking, Trekking
- Weather protectionWaterproof, Windproof
- Waterproof rating20,000 mm
- Construction3-layer
- SeasonAutumn, Winter, Spring
- Comfort temperature-2 °C
- Drop8 mm
- Size guideIn every language
Example values. You define the fields and the lists they pick from.
You stay in control
- You define the fields per category and the value lists agents pick from.
- Technical fields stay empty when no source states them, instead of being guessed.
- Every AI-written value shows its inputs, its reasoning and the prompt behind it.
- Every value keeps its history: manual edits show who made them, and earlier versions can be restored.
In and out
- Your shop and PIMTwo-way with the systems we integrate with: products in, approved values back
- Supplier filesIn whatever layout each supplier sends, joined on GTIN, EAN or SKU
- Brands' product pagesRead on the sites you allow, matched by GTIN or SKU
- Google ShoppingA feed file, ready to upload
Firtal Group
Firtal Group added a thousand extra hands without adding headcount
- products enriched
- +25K
- organic traffic to product pages
- +20%
- faster time to market
- +80%
Molly & My
Molly & My builds every market on one foundation
- products enriched across 8 markets
- 20,000
- faster time to market
- 4x
- organic traffic to product pages
- +29.3%
FAQ
Questions outdoor retailers ask us.
The specs sit with the brands. Can Cernel get them?
Yes. Most brands publish their figures on their product pages, and an agent reads them there, matched by GTIN or SKU, on the sites you allow. Figures you already hold come in with your supplier files.
Can every product type get its own fields?
Yes. Fields sit on categories, so shells get a waterproof rating, sleeping bags a comfort temperature and running shoes a drop. Subcategories inherit what sits above them, and each kind of product only shows the fields that belong to it.
What happens when a brand doesn't publish a figure?
The field stays empty. Technical fields are set up so the agent leaves a value out when no source states it. You choose which values go live automatically and which get a review step; review steps check every value and only ask a person when something fails or needs a decision. A blank field can be filled later. A wrong waterproof rating comes back as a return.
We stock 18,000 items across ten sports. Where do we start?
With one category and one field. Test it on a handful of your own products, enrich a few hundred, read the results, then widen.
Can it run on the whole range as it arrives each season?
Yes. An automation enriches every new product in the categories you choose, and can run again when the attributes you pick are updated, so the next season arrives as a review queue, not a project.
Where to next
See the part that fixes it.
- Platform
Product data enrichment
Every rating, weight and season in a field of its own, so filters and search can match it.
- Platform
External data and images
The specs a brand publishes, read from its own product pages and matched by EAN or SKU.
- Platform
Agentic review
Choose which values go live automatically and which get a review step before they do.