Customer service that scales with the season.
Where is my order, can I return this, do you have it in blue, in three languages, at ten times the volume in December. The agent answers from your order system and your policies; your team handles the customer who is upset.
Three jobs we would look at first.
Each links to the case study of how it works, what it takes and what it gives back.
Order, return and product questions
Answered from the order system and your policies, in the buyer’s language; return labels issued, exchanges offered, anything about a refund beyond the rules passed to a person.
Product content and being found
Product descriptions, FAQs and guides drafted from your catalogue, checked by you, structured so Google and AI shopping assistants can read and cite them.
The weekly sales report
Sales, returns, stock-outs and ad spend from the store, the ads accounts and the warehouse, written up every Monday with the anomalies pointed out.
what the agents take first
- Order and return enquiries
- Product content in several languages
- Weekly sales report
what stays with your people
- Complaints and goodwill gestures
- Buying and pricing
- The brand’s voice, approved by you
How it would go.
The same four steps as every engagement: a 30-minute call, a two-week prototype on your real data, a build into your tools, then we run it and count the hours.
A 30-minute call.
Where your hours go, and the two or three jobs to start with.
One job, built for real.
A working prototype on your real data.
Into your tools, tested, handed over.
Documented, with the team trained to run it.
Kept working, measured, extended.
We count the hours it saves and add the next job.
The rules every agent keeps.
Read-only first
Every agent starts by watching and drafting. It only sends, books or files on its own once you have seen it be right, step by step.
Your data stays yours
Agents run inside your own accounts and tools. Where a model is needed we use EU-hosted options by default, and nothing is used to train anyone’s model.
A person for the exceptions
Anything the agent is unsure about goes to a named person, with the facts already gathered. You decide what it may do alone, and when.
Asked by people in your sector.
Which store platforms do you work with?
The common ones; we have built and run stores on most of them since 2019. The agent connects to orders, customers and the help desk through their standard interfaces.
Can it handle the Christmas peak?
That is where it earns its keep: volume costs it nothing, and the rules do not change. Your team’s December gets quieter, not busier.
Do you know our sector?
We have built for it, and the quick-check is where we learn the rest: your tools, your rules, your week. The agent is built around them, not around a generic idea of the sector.
Start with a 30-minute call. Keep what it finds.
You tell us where the hours go. We tell you which two or three jobs AI should take first, in a short written note. Free, in English or French.