Your store, your payments and your order flow are connected once in the gateway. After that the team asks in its own words, without exporting an order list first.
One account is fine for one person. The difference shows up when a whole team uses AI, and when somebody asks what it cost or where the data went.
Everyone signs up separately. Nobody knows what it costs, who has access, or what has been shared.
One way in to every model. One login, one invoice, and you can see what is actually happening.
Claude today, something else next year. With Walma you use all of them and switch when it suits you, without redoing the work.
We have done the groundwork: ready-made connections to the tools you already use, with proven skills and instructions, so the team actually gets going instead of just trying it out.
If you want visibility, you get it: everything the agent does is visible, you get feedback on how the work could be better, and you can put a stop to things it should not do.
Walma AI Hub is a layer between your tools and the models. Here is what that means in practice.
IT approves an MCP server once. After that the tool appears for the people who should have it, with the right permissions. Nobody on the team touches an API key.
Claude, GPT, Gemini and the open models all reach the same connections. You pick the model per task instead of locking yourself in, and if you switch next year the tools come along.
When the off-the-shelf tools run out, we build. RAG over your own material, bespoke agent flows, and narrow MCP servers for systems the vendor has not covered, all running inside the same gateway and the same log.
The platforms are well covered, the payment and shipping providers less so. Where the vendor has no server we build it, and we say which ones those are.
The vendor's own server. Switched on and running the same day.
ShippoofficialCommunity-built. We review the tool descriptions and pin the version before approving.
These we build ourselves, as narrow read-only servers in your tenant. Tell us which you need first.
Centrain progress
nShiftin progress
Shipmondoin progress
Ingridin progressIncluded in every rollout.
Questions the e-commerce team already asks, minus waiting for a report first.
The gateway runs in your own Azure tenant in an EU region. Every call is logged with user, tool and arguments. That is the answer when your data protection officer asks where the data goes.
Built for European requirements from day one. Details, subprocessors and policies live in our Trust Center.
Open the Trust CenterOnly if you want it to, and then with approval per change. We set connections read-only by default, so the agent analyses sales, stock and returns but touches nothing. A wrong price in a public store shows immediately, so write access is an active decision, not a default.
Yes, though not through a ready-made server from Klarna. We build a narrow, read-only connection against their API, running in your own tenant. It is the same work behind the internal servers we already run, and it tends to be a matter of days rather than months.
Yes, through a connection we build for you. Centra is prioritised with us precisely because so much of Nordic fashion retail runs on it, and a read-only server over orders, stock and customers is a small, well-bounded build.
Shopify and Stripe have official servers. WooCommerce has a developer preview that needs a local proxy, and Adyen one in alpha for Checkout and Management. BigCommerce and Magento go through community-built servers that we review. For PayPal, Klarna and Centra we build the connection ourselves. On shipping, Shippo has an official server, and for nShift, Shipmondo and Ingrid we build.
Only what you open up. Permissions are set per role in the gateway, and the gateway runs in your own Azure tenant in an EU region, so order and customer data are processed there. For connections whose server sits outside the EU we tell you before you approve it.
Twenty minutes with an engineer. We connect your store, read-only, and show what the team can ask the next day.