From Scattered Inboxes to One Governed Service Desk

Inbound requests classified, routed and turned into draft orders, with operators approving every key step

Industry
Manufacturing

Inbound requests classified, routed and turned into draft orders, with operators approving every key step

Industry
Manufacturing

From Scattered Inboxes toOne Governed Service Desk

Client
J. J. Louro
Industry
Manufacturing
Technology
GenOS
Team
2 DareData engineers
7,000emails classified per month
500automated quotations per month
8request categories classified automatically

Results in production

J. J. Louro handles thousands of inbound requests a month across eight business functions. A governed service desk on GenOS now classifies every email, routes it to the right operator and drafts orders against live ERP stock, with people approving each order before it is sent.

The challenge

The challenge

J. J. Louro is a Portuguese furniture manufacturer, with orders, logistics, commercial, partnerships and after-sales teams serving its clients. Every request arrived by email, and people sorted it by hand across scattered inboxes.

No consistent routing

Requests landed in different inboxes and reached the right team only when someone forwarded them.

No view of response times

Without one queue, nobody could track how long a request waited or who was working on it.

Uneven workload

Some operators carried most of the load while others had spare capacity, with no way to balance it.

The solution

The solution

Using GenOS Service and Supervisor, we built one service desk for every inbound request.

A classification agent reads each email and sorts it into one of eight categories. A routing layer sends the ticket to the right team and to the operator with the least active load, with caps per person and escalation when a request waits too long.

For orders, a specialist agent extracts the client and product details, checks stock in the ERP and prepares a draft order. The operator reviews it and approves it before anything is committed or sent.

Underneath is the GenOS Platform: every action and decision is logged and traceable, so the team can monitor the desk and tune it from real production data.

The impact

The impact

  • 7,000emails classified per month
  • 500automated quotations per month
  • 8request categories classified automatically

Operators now work from one governed inbox with full tracking. Every email is classified into one of eight categories (orders, commercial, logistics, financial, administrative, product, partnerships and after-sales) and goes to the right team.

Order requests become draft orders checked against ERP stock, ready for an operator to approve. Nothing is committed or sent to a client until a person says yes.

The team

The people who built it.

  • João CalémSenior Data Scientist
  • Leonid KholkineSenior Data Scientist & Project Manager

Your AI story, next.

Tell us what you want AI to do for your business. We design, build and run it with your teams, and measure it like the stories above.

  • 01Use cases chosen for value, not hype
  • 02Systems built into your stack and data
  • 03Run, monitored and improved after go-live