Alpino AI

ERP & integration

ERP integration and interfaces

We connect your ERP to web apps, reports and AI: read-only first, and we only write after approval. Your ERP stays as it is.

Starting point

The data is in the ERP, but it is needed elsewhere

Orders, customers, items and open invoices live in the ERP. But they are needed in Excel lists, in a field-service web app or as the basis for an AI analysis. The result is double entry, manual exports and numbers that do not match. Without a clean connection, every analysis becomes a one-off project.

  • Your ERP stays as it is.
  • We read first and write only after approval.
  • Credentials stay on the server.
  • Documentation is part of the handover.

Who it is for

  • Trade and crafts

    Businesses whose orders and customers sit in the ERP but are maintained further in Excel or on paper.

  • Manufacturing and services

    Businesses that need order and inventory data in a web app or a report.

  • Mexal, XGLA and in-house systems

    Businesses running Passepartout Mexal, XGLA or an in-house ERP that want to connect this data to new applications or AI.

What we build

Building blocks, individually or combined

  • 01

    Read-only connection to ERP data

    We read master data such as customers and, as far as the interface provides them, other data such as items or open invoices through your ERP's REST/web API. If there is no usable API, a dedicated read-only user can access the database directly. In both cases, we only read.

  • 02

    Proxy for limited ERP interfaces

    Some interfaces only allow a few users and concurrent requests. A proxy on the server collects the data, caches it and protects the access key, so the application stays within the limits.

  • 03

    Writing back after approval

    Documents, orders or status changes only go into the ERP once someone has approved them. Where the ERP offers only limited write access, we clarify up front what is possible through the interface.

  • 04

    Reconciling data between systems

    A regular reconciliation keeps the ERP and connected systems in sync, for example a daily sync for a report. Discrepancies become visible instead of being silently overwritten.

  • 05

    ERP data in a web app or cockpit

    Your team sees and enters what it needs in a lean interface. Dropdowns, lists and key figures come live from the ERP and are cached, instead of from an Excel copy.

  • 06

    AI on ERP data

    With a clean connection, AI can access your order history, for example for a quote suggestion based on comparable orders. Your team reviews and approves.

What it looks like

Holler Tankwagenreinigung: web app connected to Passepartout Mexal

The tank truck cleaning company Holler wanted to record cleanings at the wash bay in a web app instead of noting them on paper and transferring them to the ERP later. The web API of its Passepartout Mexal, in the licensed scope, only allows a few concurrent users and requests, and its paged queries expire quickly. So the web app never calls Mexal itself. A proxy on the server fetches the customer master data in a single run, caches it and keeps the access key, so it never ends up in the browser. If the ERP does not respond, the app stays usable. Together with the capture at the wash bay, this gives Holler at least 50 % less time spent on documentation and 90 % fewer errors in the cleaning document.

More on the software behind it: AlpinoTank

Reference architecture

Reference architecture: capture, mediate, connect

The application never talks to the ERP directly. A proxy in between protects the credentials and the interface. This applies to Mexal as well as to other ERP systems.

  1. 1 · Capture

    Web app, form

    • runs in the browser
    • knows no credentials
  2. 2 · Mediate

    Proxy on the server

    • key stays here
    • cache, bundled queries
  3. 3 · Connect

    Web API or SQL

    • read via web API
    • or SQL read-only user
  4. Result

    Entry after approval

What we do not do

We do not implement an ERP and do not replace yours. We do not provide accounting or tax advice, and the interface does not replace the person who looks after your ERP. We do not run a helpdesk.

How we work

From concept to live operation

We start small and clearly scoped. You find out early what can be done with your data and what cannot.

  1. 01

    Concept proposal

    We clarify the starting point, data sources and open questions, and describe the solution in phases. The concept proposal deliberately does not include a price yet.

  2. 02

    Quote

    Once the open questions are settled, you receive a binding quote, either a fixed price or a range with clear assumptions.

  3. 03

    Pilot in 5 to 6 weeks

    One or two key users work with real data in their real environment. At the halfway point we show an interim status.

  4. 04

    Rollout

    All users are brought on board, training takes place on site, and handover comes with documentation.

  5. 05

    Maintenance

    Operation, model updates and bug fixes are covered by an annual contract.

Funding

Funding in South Tyrol

The Province of South Tyrol funds external innovation consulting and process innovation for SMEs with a production unit in South Tyrol. Under the provincial guidelines (as of November 2026), the funding rates for innovation consulting are 65% for small and 60% for medium-sized companies, and 45% and 35% respectively for process innovation. Whether and how much of this applies to your project depends on the individual case. The application must be submitted before the project starts. We support you with the application and, if you wish, prepare it in full. We cannot promise funding, but in the intro call we assess what is realistic.

Related use cases

  • Craft manufacturing company · South Tyrol

    Quotes in minutes instead of hours

    Situation
    For every customer request, sales manually searches the order history for comparable jobs, estimates price and effort, asks colleagues and assembles text blocks. Different salespeople calculate the same job differently. Margins are not enforced systematically.
    Solution
    We connect ERP history with an AI module that finds comparable orders and suggests a price corridor — including effort estimate and suitable text blocks. Sales sees the proposal, reviews it, adjusts it and approves it.
    Outcome
    Quotes are created in minutes instead of hours. Similar jobs are calculated consistently across the sales team. Margins can be managed more deliberately because the data basis is visible.
  • Wholesale · South Tyrol

    Automating debt collection and receivables management

    Situation
    Payment reminders are sent one by one. Nobody knows which customers chronically pay late and which are only late once. Liquidity suffers, and accounting loses time on routine emails.
    Solution
    We analyse historical payment data and group customers by payment behaviour. Reminders go out automatically — via WhatsApp or email, in the right language, at the right time. A human approves every escalation level.
    Outcome
    Accounting no longer handles standard cases manually. Early payment delays are detected sooner, liquidity improves, and difficult cases get the attention they need.
  • Electrical and systems engineering · South Tyrol

    Digital assistant for a trades business: materials, extra work and technical questions by voice

    Situation
    Installers interrupt their work to record materials in several apps. Reports on extra work and service completions consist of many individual steps, and answers to technical questions are scattered across manuals, data sheets and project files.
    Solution
    Alpino AI builds an assistant for the smartphone: employees speak, take a photo or type. It queries stock levels in the ERP, prepares material requests and work reports as drafts and answers technical questions with a source.
    Outcome
    A few steps instead of many entries, with bookings that reach the ERP automatically once confirmed. The assistant suggests, the person confirms, and every action is traceable.
  • Manufacturing · South Tyrol

    AI platform for a manufacturer: knowledge, sales and planning on one data basis

    Situation
    Technical knowledge sits in data sheets, certificates and manuals, customer knowledge in the ERP and mailboxes, planning often in Excel. Every question about a product, customer or stock level means a separate search.
    Solution
    Alpino AI builds a platform with its own data basis and three modules: knowledge search with sources for engineering, customer and order analysis for sales, and forecasting and production planning for the supply chain. Connections to the ERP, file server and email run through a shared layer.
    Outcome
    Access to the data that knows roles and permissions and backs every answer with a source. New modules build on the basis without rebuilding connections. The decision stays with people.
  • Print and packaging manufacturing · South Tyrol

    1,500 die-cutting forms become a searchable 3D library

    Situation
    A historically grown collection of around 1,500 die-cutting forms exists partly as print data (PDF/vector) and partly as physical samples. Sales and production need minutes to hours to find the right form for a customer request — there is no central overview.
    Solution
    We parse cut and crease lines from print files, automatically generate a 3D model of each die-cutting form and store everything in a searchable asset database. Search works by dimensions, product type, material and similarity embeddings — for example “folding carton ~10×6×4 cm with tuck closure”. Links to ERP orders and calculation are included.
    Outcome
    Knowledge that used to be scattered across people’s heads becomes a searchable library with preview renderings. Sales can immediately compare customer ideas with existing inventory, production sees historical usage — and new die-cutting forms can be compared with similar existing forms before ordering.
See all use cases

Frequently asked questions

Regional

Based in Brixen, on site in South Tyrol

We are based in Brixen and work with businesses throughout South Tyrol. Looking at the ERP together, clarifying access and responsibilities with your ERP administrator and supporting the connection in your business: that works with short distances and in German or Italian.

About Alpino AI

Next step

Which data is stuck in your ERP?

Tell us which ERP you use and what you plan to do with it. Together we check how the data can be connected, and we will tell you honestly if it is not worth it.