- AI AUTOMATION
- AGENTIC AI
- SENIOR ENGINEERING
I automate work between people, documents, and software.
I build AI assistants, agents, and workflows that understand information, use tools, and take on clearly defined tasks. I have worked with agentic AI since 2023—on a foundation of 15 years in software engineering and around ten years in complex e-commerce systems.
- Agentic AI since 2023
- 15 years in software engineering
- Documents · browsers · knowledge · APIs
- Remote for DACH
WHAT CAN BE AUTOMATED?
Four kinds of work that no longer need to stay completely manual.
I work across industries. The deciding factor is not whether a process sounds like AI, but whether knowledge, data, tools, and recurring decisions can be connected usefully.
Understand and process documents
AI reads varying formats, extracts relevant information, and prepares the next step.
- PDF, email, or scan → structured data
- Plausibility check → approval or clarification
- Transfer into ERP, CRM, or specialist software
Find knowledge and prepare cases
An internal assistant researches approved sources, combines context, and keeps results traceable.
- Search internal documents and knowledge bases
- Prepare support, review, or operations cases
- Answers with sources and access rules
Operate interfaces without a suitable API
A constrained browser or desktop agent handles recurring steps and returns unclear cases to people.
- Supplier, customer, or administrative portals
- Documented actions instead of blind autonomy
- Escalation when cases deviate or fail
Coordinate work across systems
APIs, rules, conventional workers, and AI form one workflow instead of handing every step to a language model.
- Reconcile data and explain discrepancies
- Select tools based on the case
- Measurable handoffs, approvals, and results
AGENTIC AI SINCE 2023
What excites me about agentic AI.
Hardly a week goes by without new models, tools, or development environments. I follow this work with genuine curiosity and try many of them myself. It becomes exciting when a new capability turns into a useful workflow: a document is processed reliably, an agent uses a tool sensibly, or a process genuinely takes work off someone’s plate. Experiencing how quickly the possibilities are expanding—and turning them into solutions that work—is something I am thoroughly enjoying right now.
WAYS TO START
Build, validate, or enable: the entry point follows your goal.
Some teams know the process and want to build. Others first need to find the leverage or test a technical uncertainty. Implementation is my core offer; analysis, prototyping, and workshops are possible entry points.
AI automation and agents
I design and implement a constrained workflow, connect the necessary systems, and define measurement, approvals, and operations.
Opportunity mapping and prototype
When value or feasibility is unclear, we prioritize processes and test the riskiest technical step with representative data.
Workshops and technical sparring
For teams that want to build or make better decisions: agentic AI, AI building, safe coding workflows, and realistic use cases.
DPP & AGENTIC COMMERCE
The product passport could become the trusted information layer for agentic commerce.
Today I automate real business processes. In parallel, I work on the infrastructure that agentic commerce will need tomorrow. AI buyers need more than marketing copy: stable product identity, structured attributes, origin, evidence, versions, and permissions. That is precisely the information layer the Digital Product Passport must build. My thesis: companies that solve DPP well do more than prepare for compliance—they make products discoverable and processable for agentic markets.
The important questions before an automation project.
New capabilities are exciting. A good project still needs concrete value, data, responsibility, and operations.
Do you only automate e-commerce processes?
No. I work across industries with documents, internal knowledge, browser interfaces, APIs, and existing software systems. E-commerce is my technical foundation: around ten years of connecting complex, established, and business-critical systems reliably.
Does every process need an AI agent?
No. Known, stable steps usually belong in an API, import, or conventional worker. An agent becomes useful when context is incomplete, tools depend on the case, unstructured information must be understood, or exceptions need handling.
What does agentic AI mean at EinfachAI?
An agentic system does more than answer a question. Within defined boundaries, it can gather information, use tools, perform actions, check results, and escalate difficult cases. The process—not the demo—determines how much autonomy is appropriate.
How do you handle sensitive data and dependencies?
Data minimization, access control, model choice, logging, and hosting are architectural decisions. Where useful, I consider European hosting, open models, and interchangeable components. Sensitive data is not automatically passed to public models.
What work should your team no longer perform manually?
Show me a recurring process. I will give you an initial assessment of whether conventional automation, an AI workflow, an agent, or no project at all is the right next step.