Retail and e-commerce
Your shop’s own AI.
Customer service and product data in every language, from the shop’s own history.
Yes, within your return period, with the receipt 1. Sale items are exchanged or refunded as store credit 2.
- 1Returns policy
- 2Sale terms
Illustrative
- Tasks to start with. A Test Lab takes one.
- 3
- The Formula it starts withWith TLM
- LLM
- To roll back to the last release, by design
- 60 s
- Eigna Cloud. Data stays in the region you choose.
- Cloud
The work that cannot leave
Your customers, your catalogue and your service history are your advantage. A rented model gives your competitors the same answers.
- Customer records
- Service history
- Catalogue and prices
- Sales history
Where it runs, for retail
Eigna Cloud
Data stays in the region you choose.
A dedicated GPU in the region you choose, run by us.
Your data sits on your own volumes in our GPU region, with keys you hold.
The first expert
Three tasks to start with.
Answers and texts approved by your team.
Customer service
Answers in your tone, from your own policies.
Yes, within your return period, with the receipt 1. Sale items are exchanged or refunded as store credit 2.
- 1Returns policy
- 2Sale terms
Learns from · Answers your service team approved.
Product data
Descriptions and attributes in every language.
Two drafts in your tone, with care instructions from the supplier sheet 1 and sizes from the catalogue 2.
- 1Supplier sheet
- 2Catalogue entry
Learns from · Descriptions your editors approved.
Demand forecasts
From your own sales history.
More for the northern stores, about the same elsewhere 1. Last year’s early cold spell is marked as unusual and counts less 2.
- 1Sales history, footwear
- 2Weather notes, last winter
Learns from · Orders your buyers placed, and your sales history.
The proof we will measure
A metric, a baseline and a sealed test, agreed before we start.
The target is set with you before the Test Lab starts. If the expert does not beat your baseline, you keep the report.
17.8%
Our first training run cut forecast error 17.8% against its base model. It is not yet ahead of a simple last value baseline, and we publish that too.
Rules in plain words
What the rules ask, and what every release gives you.
- 01
People know it is AI
From 2 August 2026, the EU AI Act asks that people know when they talk to an AI.
- 02
Your history trains your model
Your catalogue and service history train only your model, and never move between clients.
- 03
A cost you can plan
A fixed running cost instead of a bill per token. For light use of the cheapest rented models, renting stays cheaper.
Retail and e-commerce
Your history trains your model.
Your catalogue and service history train only your model and never move between clients, at a fixed running cost instead of a bill per token.
Retail: questions and answers
Does it answer customers directly?
Where you allow it. You choose which answers go out on their own and which a person approves first.
When does owning pay?
With heavy, steady use: many questions a day, many products, many languages. For light use, renting stays cheaper.
Where does customer data go?
With Eigna Cloud it stays in the region you choose, on your own volumes, with keys you hold.
Test Lab
Request a Test Lab for retail.
One task, your data, a sealed setup, about four weeks. If the expert beats your baseline, the test set becomes your first release gate. If not, you keep the report.
- RouteDirect, and through commerce agencies.
- Watch forIt pays for heavy, steady use. For light use, a rented model stays cheaper, and we say so.
- ReplyWithin two working days, from a founder.
