[ hello & welcome ]
I understand the challenges in your business and bring the right technology to solve them. As an industrial engineer, I connect business and technology where it counts: measured by impact and ROI, from solution concept to systems running in production.
[ profile ]
Most companies don't lack AI potential, because their people already bring concrete ideas to the table. What's missing is execution. That's exactly where I come in: as a consultant, I develop the solution concepts and put the right technology in the right place. And as a solution engineer, I help build the systems that realize the potential.
My foundation: as an industrial engineer (M.Sc.) specialized in operations management with a data-science background, I have spent my entire career resolving process bottlenecks through optimization and automation. Working with me gets you both: the concept that scales, and the hands that deliver.
[ services ]
[ consulting ]
Potential analysis and identification of the right use cases. Because not every challenge should be tackled with AI, only where it truly makes sense.
[ engineering ]
Solution concepts that fit and grow: tailored to your use case and designed for scale from day one.
[ development ]
Development and deployment: I build the specialized tools and actions your processes need, and bring them into productive use.
[ integration ]
Seamless connection of your data sources and business systems: the right data, in the right quality, at the right time, in the right place.
[ projects ]
Each of these references stands for the same principle: a real business challenge, a sound solution concept, and a system running in production today. Unnamed for confidentiality, but concrete in substance.
[ erp × agents ]
delivered
An ERP system fully exposed as an MCP server, operated by AI agents instead of humans. Employees talk to a supervisor agent that applies the right skills per task and spawns subagents on its own.
impact
Administrative work by natural language instead of click paths. Operations get faster because end-to-end processes run automated without manual steps in between.
[ agent platform × governance ]
delivered
No-code platform where business users build and visually orchestrate their own AI agents, including a governance layer, approval guards, and a human-in-the-loop inbox.
impact
AI scales across departments without losing control: every agent action stays traceable, and critical steps require human approval.
[ deep research × sales ]
delivered
Research agents analyze target companies, derive fitting AI use cases (farming), and generate validated contact lists for target markets (hunting).
impact
Sales walks into every conversation prepared: individually researched talking points instead of generic pitches, in active use every day.
[ forecasting × food craft ]
delivered
Forecasting platform that unifies sales data from stores, webshop, and vending machines and predicts daily demand using weather and holiday features.
impact
Production and procurement planned on numbers instead of gut feeling: less overproduction and write-offs, better availability.
[ graphrag × insurance ]
delivered
A knowledge graph combined with vector search (hybrid RAG) that structures complex insurance policies and derives individual recommendations matched to each customer's situation.
impact
Faster, better-fitting recommendations: insurance coverage matched to the individual situation instead of the average case.
[ approach ]
AI not as an island solution but as your target operating model: fully integrated into your processes, with the data and systems you already have.
Roles, processes, responsibilities, and audit keep technology anchored and secured instead of fading out after the pilot.
Flexibility in how your solution is built, from no-code workflows to custom development. That realizes the full potential without the limits of off-the-shelf tools.
The right data, in the right quality, at the right time, in the right place: data architecture and integration form the foundation of every decision.
[ technology ]
Coding agents support me in specifying, verifying, and documenting code. The result: fast demonstrators and clean, well-documented tests.
I use the full spectrum from no-code to low-code to code, so realizing your potential never fails at a tooling limit.
Not every problem needs a language model. Where it fits, I rely on classical machine learning, deep learning, and natural language processing.
The basis of every reliable AI application is its data foundation: from tabular to vector to document and graph databases.
Scalable, low-maintenance operations require clean architecture, logging, monitoring, and CI/CD from the start.
Frontend and backend frameworks that speed up development, without cutting corners on security and scalability.
[ contact ]
Whether it's first ideas, concrete use cases, or solutions already built and about to scale: I look forward to exchanging experiences.
LangGraph
MCP
FastAPI
Next.js
Postgres / pgvector
Langfuse
Django
Elasticsearch
React
Neo4j
LangChain
Gatsby
.svg)
