A Swiss engineering company Over twenty years in business

Engineering software that has to keep working.

Artabel is a Swiss engineering company. We build information systems, industrial instrumentation and applied AI for industry, healthcare and cultural institutions. Our oldest system has been in daily production at an aluminium plant since 2008.

2004 Founded
2008 The Confal enterprise platform has run in daily production since
2015 The EPFL decision-support mandate has run since, and is still running
4 Areas of work: applied AI, enterprise software, systems integration, instrumentation

Where our systems run

Aluminium smelting · SK Semiconductor manufacturing · INT University Hospital of Basel · CH EPFL laboratory safety · CH Real-estate asset management · CH Technical university VR lab · SK Open-air heritage museum · CH

What we do

Four areas of work.

Artabel covers both the modelling and the engineering that puts it into service — integration, access control, release, and the years of maintenance afterwards.

01

Applied AI

Retrieval and document intelligence, computer vision, speech and structured extraction, predictive modelling, data-centric AI.

02

Enterprise software

Configurable workflow and information systems with role-based access, approvals, reporting and analytics, built to be maintained for a decade.

03

Systems integration

Connectors, APIs, data pipelines, migration and deployment into estates that were never designed to be connected.

04

Instrumentation & 3D

Sensing and smart devices in hostile environments, real-time tracking, plus 3D visualisation and immersive interfaces.

Selected work

Selected systems.

01 — VRPIS · 2008–present

A configurable enterprise system, in continuous production since 2008

Role-based workflow, document circulation and approval, procurement, inventory, logistics, accounting, reporting and external-system integration — deployed at Confal, Slovakia’s largest producer of aluminium alloys. Permissioned data flows, release control and auditability, in continuous use since 2008.

02 — LARA · EPFL Lausanne · 2015–present

An expert method turned into auditable decision-support software

Artabel translated a specialist laboratory risk-assessment methodology into structured data capture, transparent calculation logic, corrective-measure assessment and reportable output. Domain rules encoded so a human can inspect them; bounded decisions; explicit human authority at the point of judgement.

03 — Document intelligence · 2023–present

Source-grounded retrieval across an eight-year archive

Ingestion, OCR and metadata extraction feeding semantic search, source-grounded generation and assisted analysis under human review — with AI-driven classification, reputation monitoring and a portfolio dashboard on top. Every answer carries a citation to the source document and page it came from.

Research projects

Engineering in funded research.

Artabel contributes software engineering and systems integration to European research projects: interface design, reusable components, testing, deployment and handover.

Method

Measured before it ships.

Every Artabel engagement is judged against a measure agreed before it starts: a baseline taken from the method already in use, a test set that reflects the real task, error analysis weighted by what an error costs, and sign-off by someone qualified to judge the output. Where the work carries professional or safety consequences, a named person approves each release.

How we work

Scope, prototype, validate, implement.

Four stages, each ending in a decision you can act on: whether the data supports the task, whether a prototype behaves, whether the measurement holds, and whether the system is ready to run in your environment.

Next step

Tell us about the task.

Describe the problem and the constraints around it, and we will tell you whether it is work we can do.