Automate repetitive business work such as copying data, generating documents, handling approvals, validating imports, and preparing reports.
I use APIs, scheduled jobs, document workflows, and small internal applications where they fit the process. Many automation problems do not require AI. I only use AI in a workflow when its accuracy can be measured, uncertain cases can be reviewed by a person, and the process still works when the model fails.
Foodtech company (confidential) · 2025
Developer, through VertexWare
A Python tool that predicts characteristics of a food formulation from its inputs, with a confidence value and an explanation for every result.
Kleiberit GmbH · 2019–2023
Software developer in a dual study programme (Business Information Systems)
Process software, role-based access, laboratory workflows, and legacy application work inside a manufacturing organisation.
Generate reports straight from your application's data, from an overview of every record to a full report on a single one. Move data out of old systems without losing records, and get estimates that show how they were reached.
Use language models where a workflow has to read or sort messy input, with checks and human review around them.
Connect the systems you already use and build the tools needed to fill the gaps between them.
Modernise critical software without a big-bang rewrite.
Take over software that no longer has a reliable maintainer.
A short conversation is enough to decide whether an audit, a small build, or no custom software is the right next step.