LLM adoption for e-commerce teams
Open models.Our hardware.Your data stays yours.
Most consultancies resell someone else's API and bill you per token. We pick the open model that actually fits the job — weighed against independent benchmarks and proven on your own data — and run it on hardware in the EU that we control, so your catalogue, tickets and customer records never leave it.
What you can do with it
Ten jobs your business already does by hand.
One from each corner of the library: support, search, catalogue, translation, marketing, sales, logistics, bookkeeping, internal knowledge, customer feedback. Some answer a customer while they wait; others chew through the whole catalogue overnight.
Draft answers to where-is-my-order emails
Customer service
Looks up the real order and tracking status and drafts a reply with the carrier's information, ready for an agent to approve and send.
Answers while someone waits
Let shoppers search in their own words, not your catalogue's words
Search & discovery
Meaning-based search next to your keyword search, so loosely phrased queries find the right products even when no words match your titles.
Answers while someone waits
Turn supplier spec sheets into first-draft product descriptions
Catalogue content
Drafts product descriptions overnight from the supplier data you already hold, in your shop's voice — a review job instead of a from-scratch writing job.
Runs in bulk, overnight
Translate your product catalogue with your own word list locked
Selling across languages
Draft catalogue translations into EU languages with your brand, material and category terms applied from your own glossary, ready for review.
Runs in bulk, overnight
Draft replies to customer reviews
Marketing
Drafts a reply to each new review in your tone, grounded in your past replies and policies. Nothing is posted without a person approving it.
Answers while someone waits
Draft a quote from a customer's enquiry email and your price list
Sales & B2B
Turns an inbound enquiry and your price list into a filled-in quote draft for a salesperson to check and send — a document to correct, not a blank page.
Answers while someone waits
Pull order lines out of supplier PDFs and emails into a spreadsheet
Operations & logistics
Extracts SKU, quantity, price and delivery date from supplier PDFs and emails into rows you can import into your ERP or a spreadsheet.
Runs in bulk, overnight
Pull the details off supplier invoices into your bookkeeping
Finance & admin
Pulls supplier name, invoice number, dates, line items and VAT out of PDF invoices into records your accounting software can import.
Runs in bulk, overnight
Let staff ask the handbook a question instead of asking HR
HR & internal
A private chat box that answers staff policy questions from your own handbook, with a link to the exact section. Runs entirely in Amsterdam.
Answers while someone waits
Draft a 'what buyers say' summary for each product page
Voice of customer
Drafts a short, balanced 'what buyers say' block for each product page from its reviews — into a review queue, never straight onto the site.
Runs in bulk, overnight
The API is cheaper per token. Here is why our customers don't use it.
We will not pretend otherwise: renting a model by the token from a serverless API costs less per million tokens than a card we run for you. We show that price on every use-case page. What it does not include is the part a shop with a customer database actually pays for.
- 01
Your data never leaves hardware you can point at
A serverless "we don't retain your data" is a clause in a contract. Running the model on a card in Amsterdam is a fact of architecture: your catalogue, tickets and customer records are never sent to a third party at all. For a GDPR audit, that is the difference between a promise and a floor plan.
- 02
The price cannot move without your say-so
A serverless rate card is somebody else's lever. The provider can raise the price, retire the model, or change the terms, and your cost moves with it. The same model on the same card costs the same next year — you own the number.
- 03
The model cannot be taken away
Hosted APIs deprecate models on their own schedule; the one you built on can be gone in a quarter. An open-weight model on your own hardware runs for as long as you keep the lights on. No vendor can end-of-life it out from under you.
And the price gap closes with volume: past a card you keep busy — very roughly four billion tokens a month — owning is cheaper outright, even before the three reasons above.
Next
The whole library
Every job we know how to hand a model, with the data each needs and the point at which it stops being useful.