— AI & Consulting

AI and consulting

Alongside teaching, I have spent more than twenty years as a network architect, with a focus since 2024 on generative-AI systems. If you have a concrete daily-work problem to solve with modern agents, get in touch.

— Where AI pays off

Where AI pays off

In Germany AI use is rising fast; missing skills and privacy concerns still limit depth. Globally, agents pay off when work is repetitive, document-heavy, and reviewable — Cursor, MCP, and RAG with verify loops, not chat demos.

— What I offer

MCP servers and agents

Production-grade MCP servers (Model Context Protocol) that expose your internal APIs, databases, and tools to LLM agents — with clear boundaries, logging, and verification.

Agentic workflows with Cursor

Structured agent pipelines using the Plan → Execute → Verify → Iterate pattern. Domain-specific Cursor rules, skills, and anti-hallucination checks for real engineering tasks.

Transformer fine-tuning

QLoRA fine-tuning of 7B-parameter models (StarCoder2, Qwen2.5) on bespoke datasets with PyTorch, TRL, and PEFT on GPU hardware — when RAG alone is not enough.

RAG and graph-based systems

Retrieval-augmented-generation pipelines on LlamaIndex and vector databases; graph modules for structured analysis across domain documents and configuration sources.

— How this helps daily work

How this helps daily work

Inbox and reply drafts

Hours in email, uneven tone, the same thread shapes every week.

An agent drafts replies in your voice for approval — faster, never sends on its own.

Calendar and invite triage

Invite pile-ups and manual weighing of rules and priorities.

Rules-based triage: accept/decline suggestions so the calendar stays usable.

Repetitive portal clicks

Training portals, forms, and internal UIs burn minutes on every pass.

Browser agents run the click paths; you only handle exceptions.

Scanned documents

Contracts and statements as image PDFs — not searchable, painful to extract.

OCR plus structured extraction: searchable text and less retyping.

Engineering with Cursor agents

Generic AI invents APIs and breaks production systems.

Rules, skills, and verify loops: repeatable agent work with measurable checks.

Internal APIs via MCP

Know-how is trapped in CLIs and GUIs; only specialists can move.

An MCP server over your APIs: natural-language questions, actions with verification.

RFQ compliance with RAG and agents

Hundreds of compliance questions in Excel; evidence spread across PDFs and decks; manual scoring takes days.

RAG over product docs plus MCP tools and a local LLM: evidence-backed verdicts with an audit trail; super-agent eval replaces copy-paste. Helps human compliance writers answer thousands of hard questions quickly and ground each answer in many different data sources.

Internal knowledge Q and A

Years of expertise sit in drives and mail threads; new hires ask the same questions every week.

RAG over internal docs with citations; specialists only review the hard edge cases.

Codebase migration with agents

Large migrations stall in planning; hand rewrites burn months of calendar time.

Cursor rules and verify loops move migrations faster while humans keep the review gate.

Security questionnaire drafts

Vendor security forms repeat policy text across dozens of portals every quarter.

First drafts grounded in policy docs; humans approve before anything is sent.

— Case study: questionnaire under deadline pressure

Case study: questionnaire under deadline pressure

Problem

A bid team must answer hundreds of technical questions in Excel. Evidence lives in PDFs and decks. Manual search and retyping costs days and yields uneven wording.

Approach

We build a RAG layer over product docs, MCP tools for search and extraction, and a super-agent eval loop — optionally on a local LLM. Every answer stays approval-gated and carries sources in an audit trail.

Outcome

Compliance writers get grounded drafts in hours instead of days. Humans still own risk and wording; the AI owns research and first structure.

— Tools & stack

Tools & stack

Python · FastMCP · LlamaIndex · PyTorch · TRL/PEFT/QLoRA · Hugging Face · Cursor (Agent Mode) · MCP Protocol · Git/GitHub · SSH · Conda.

— How I work

How I work

Start small, verify early, roll back often. No hype demos — I build systems that run in production and leave behind code, tests and documentation.

— FAQ

Frequently asked questions

What is an MCP server and when do I need one?
MCP (Model Context Protocol) is an open standard that lets LLM agents — Cursor, Claude, custom assistants — talk safely to external systems: databases, APIs, your own software. If colleagues run Cursor and need to reach internal infrastructure, a dedicated MCP server is usually the right architecture.
Do you work remote, or only in Bavaria?
I work AI engagements largely remote — that is the industry norm. Workshops and longer on-site engagements I prefer around Ingolstadt, Munich, Augsburg and Bavaria. Germany-wide by agreement.
What specific generative-AI experience do you have?
Full-time since 2024. Production MCP servers over orchestration and planning APIs. RFQ compliance assistants with RAG and super-agent eval (including local LLMs). QLoRA fine-tuning on bespoke data. RAG pipelines with LlamaIndex. Agentic workflows with Cursor. Before that, 20+ years as a network architect.
What does AI consulting cost?
Hourly and day rates by arrangement — depending on scope, complexity, and travel. An initial scoping engagement (typically half a day) can often be flat-rated. Send a short description of what you have in mind and I will reply with an estimate.

Send an inquiry

Briefly describe the project in the contact form. I will reply with an assessment.

Go to the contact form →