Insights | Discover our latest work

An AI mailbox assistant for BelOrta

Written by Stef Ceyssens | Sep 29, 2025, 10:00:00 PM

BelOrta is one of Europe's largest fruit and vegetable auctions. Every day, orders, delivery questions, changes and complaints arrive by email from supermarkets, wholesalers and caterers — and every one of those emails is a link in the operation. Cloudway built the AI mailbox assistant that now sorts them, without BelOrta changing a single thing about how its people work.

A clear structure meeting an untidy reality

The needs of BelOrta

BelOrta works with three specialised teams — Vegetables, Fruit and Organic — and each runs its own mailbox. On paper that is a clean split. In practice, customers do not know which team handles what, and they have no reason to care. A question about conventional fruit arrives in the organic mailbox. An order goes to all three at once, on the reasonable assumption that at least one of them is the right one.

The volumes turn that into real work. The vegetables team receives around 110 orders a day, 25 of which are not theirs. Fruit receives 70, of which 50 are meant for someone else. Organic receives about 100 a day — and roughly 90 of those turn out not to be relevant.

So before anyone can act on an email, somebody has to read it, work out whose it is, and move it. Every day, in three mailboxes. BelOrta wanted that to stop, without adding a new system for their teams to learn.

Intelligence behind the mailbox, not in front of it

The design decision that mattered most was made early: no new platform. The assistant sits behind the existing Outlook environment. Nobody was asked to adopt a tool, log into a portal or change a habit. The intelligence went in behind the scenes.

Every incoming email is analysed automatically — and not just the message. Attachments are read too: PDFs, Excel files and images, which is where the actual order information usually lives.

From that analysis the assistant answers two questions in order. First, does this email belong in the mailbox it landed in? A fruit order in the organic mailbox is flagged as not relevant for organic; a vegetable order in the fruit mailbox is recognised and labelled as such. Second, what kind of message is it — a new order, a question about an existing one, or a complaint? Each relevant email is filed into the right folder on that basis. The mailbox arrives sorted.

Because customers write in more than one language, the classification works on the meaning of the message rather than on keywords, so the same rules hold whichever language an order comes in.

The content stays where it belongs. Emails and attachments are processed inside BelOrta's own environment, are not shared with other organisations, and are not used to train external AI models.

Business logic beats botany

The most interesting problem on this project was not technical. It was working out what counts as fruit.

Botanically, a tomato is a fruit. At BelOrta a tomato is a vegetable, because that is how its customers order it and how its teams work. Several exceptions like that surfaced during the project, and each one mattered: an assistant that classifies produce correctly in theory and incorrectly in practice is worse than no assistant at all, because now somebody has to check it.

So the solution was tuned to BelOrta's own product logic rather than to a general-purpose one. The system categorises produce the way BelOrta categorises produce. That is the difference between a generic AI model and something that actually fits an operation — and it is usually where the real work of an AI project sits.

Cloud native technologies used

  • Cloud services: Microsoft Azure — Azure OpenAI for the semantic analysis, Azure Logic Apps for the workflow
  • Language & runtime: JavaScript on Node.js, with Express
  • Delivery: containerised with Docker
  • Integration: the existing Microsoft 365 and Outlook environment — no new end-user platform
  • Document handling: automated extraction from PDF, Excel and image attachments

The result: a working day with less sorting in it

  • The manual triage is gone. Staff work in Outlook exactly as before. What changed is what they no longer do: read an email to find out whose it is.
  • Misdirected mail costs nothing. On the fruit mailbox that is 50 messages a day that no longer need a human to redirect them — and customers can keep sending mail wherever they like.
  • Every mailbox has a daily picture. How many new orders came in, how many questions are open, whether there are complaints that need priority. That feeds capacity planning and reporting, not just the inbox.
  • Confidentiality is preserved. Customer and order data stays inside BelOrta's environment.
  • It was a short project. The assistant was built and delivered inside a two-month engagement, on top of systems BelOrta already had.

This is what a lot of useful AI looks like. Not a transformation program but an everyday process organised more intelligently, with no new tools and no change management, giving back time, focus and oversight. Sometimes innovation is not doing something new, but doing something you already do every day rather more cleverly.

Do you have a process where people spend their day sorting, routing or re-typing what a system could read for them?

our experts are happy to look at it with you.