Claude Experts in Munich

• A recurring problem in my own AI-supported projects: requirements analysis, use cases, and architecture decisions can be created quickly with AI support, but they remain hard to trace and scattered across Markdown files – knowledge is lost as soon as it is no longer in the context window. arknet turns requirements engineering and architecture knowledge into structured, verifiable data instead of plain text: requirements, use cases, and architecture decisions as a continuously linked knowledge graph, traceable from the requirement to the architecture decision – queryable for both people and AI agents alike. Technically based on RDF/OWL and its own MCP server.

• Result: MCP daemon running, Docker image automatically published on GHCR, nine hexagonal modules, eleven ADRs (including an open-core licensing model). Requirements engineering and ubiquitous language hexagon active. Publicly available since 07/2026 as a Community Edition under Apache-2.0 (github.com/kogn-io/arknet), together with the Claude Code plugin and the GHCR image; open-core model.

• Label: Java, Maven, RDF, RDF4J, OWL, SPARQL, Model Context Protocol, Spring AI, Docker, GitHub, Git, Claude Code, Obsidian, DDD, Hexagonal Architecture, ArchUnit, JUnit, AssertJ

• Consulting across two integrated areas: Commercial Strategy (pricing, sales steering, marketing strategy, market expansion, margin management) and Operational Efficiency (process automation, AI integration, workflow design, last-mile automation).
• Development of custom SaaS solutions, explicitly tailored to the specific requirements and processes of each company.
• Delivery of AI training and change management workshops for managing directors and specialist departments, including AI competence training with a certificate of attendance under Art. 4 of the EU AI Act.

• Designed role-based delivery assignment workflows, switchable between own fleet and partner carriers, with traceable status chains from „pending“ to „in delivery.“
• Designed AI-assisted route optimization, where dispatchers review drive-time-optimized route suggestions as drafts and apply them in one click.
• Designed a central planning interface for delivery and route management, bringing table view, map view, and route composition into a single workflow.
• Built interactive prototypes to align new product features early with stakeholders and engineering.

Key methods: AI-assisted Product Design, Workflow Design, Role-Based Workflows, Dashboard Design, Interaction Design, Prototyping, Logistics/Operations UX, Stakeholder Collaboration

• Designing AI-first workflows that integrate AI into existing product experiences
• Developing UX concepts for prompt management, reusable and combined prompt workflows, tagging, search and information organisation
• Creating user flows, wireframes, prototypes and high-fidelity interfaces in Figma
• Defining reusable UI patterns, components and interaction logic for scalable products
• Exploring human-AI interaction patterns with emphasis on user control, transparency and manageable cognitive load
• Translating product requirements and technical constraints into developer-ready UX/UI specifications

Independent product design practice supporting startups and growing companies with enterprise SaaS, workflow architecture, product strategy, and AI-enabled product development.

• Deliver end-to-end product design for digital products, websites, and SaaS platforms, combining product thinking, UX, visual design, and implementation.
• Apply AI throughout the product lifecycle—from research, synthesis, information architecture, and prototyping to development, SEO, and content strategy.
• Design and build production-ready digital products using AI-assisted workflows, enabling significantly faster iteration and delivery.
• Advise founders and businesses on product positioning, UX strategy, and digital transformation.

I help companies and digital teams win back time in their day-to-day work – by automating recurring processes and improving digital products in a targeted way. Depending on the need, either in execution or at leadership level (interim).

Typical results:

• Manual routine processes run automatically – requests, data maintenance, follow-ups
• Faster response times and fewer things left sitting in day-to-day operations
• Clear priorities in product and digitalization initiatives, practical instead of overbuilt

How: modern No/Low-Code automation (including n8n, Make.com), combined with experience as a Managing Director and digital product lead. The tool is never the starting point – the question is always where a solution creates real value.

• Build and operate an end-to-end MLOps platform on Azure ML and Kubernetes (Kubeflow) for the automated deployment, monitoring, and scaling of forecasting models (including Temporal Fusion Transformer, Informer, Autoformer).
• Implement CI/CD pipelines in Azure DevOps for the full ML lifecycle – from resource provisioning (Terraform), data transformation (Hugging Face Datasets, Pandas, PyTorch, CUDA cluster) through training and evaluation to model registry and endpoint deployment.
• Integrate MLflow for experiment tracking, model versioning, performance monitoring, and automated registration in the Azure Model Registry.
• Develop and containerize PyTorch training jobs (Azure Notebook, Jupyter Notebooks) for price and time series forecasting (PFC models) with automatic rollout via Azure ML Endpoints and REST/gRPC interfaces, Docker containerization, secured with OAuth 2.0.
• Set up monitoring and alerting mechanisms (Prometheus, MLflow Metrics), log centralization, and cost monitoring.
• Automate infrastructure provisioning and model deployment using Terraform, Helm, and Azure CLI; connect to existing market data systems and event pipelines.
• Migrate existing workloads and databases (IONOS → Azure, MongoDB) with integration into central MLOps workflows and internal networks.
• Extend the platform with LLM-based tools (LangChain, LangServe) to integrate GPT-based analysis modules into existing Spring Boot services for market anomaly detection and automated reports.
• Analyze and architect a software solution to process large volumes of data efficiently (>3000 messages/sec.) (market data store).
• Spring Boot / Java 21 container development with RabbitMQ for distributing stock market data via MongoDB (Kubernetes) with fast storage of data in Redis RMaps, deduplication, forwarding messages to Read Model queues, and building Read Models for UI display in MongoDB.
• Integration of RESTHeart to create a REST API for MongoDB.
• Build an Angular frontend to simplify data queries and master data maintenance.
• Agentic coding with remote and local LLMs (Claude Sonnet, Ollama Qwen) and MCP servers.
• Develop Python scripts for transforming and cleaning incoming stock market data (Pandas, scikit-learn).

• Governed multi-agent orchestration for regulated, EU-based companies – self-hostable, compliant with the EU AI Act and GDPR („by design“), BYOM (own models/GPU).
• Two-gate governance: agent deliberation + mandatory human approval, full signed audit trail; graduated autonomy model („internal → autonomous per skill“).
• Verified knowledge graph („Company Brain“) with source evidence for every answer; own orchestration framework (Virtual Team Framework).
• Industry solutions for financial services: compliance monitoring, invoice and contract review; hands-on development with LLMs (including Anthropic/Claude), agentic workflows, RAG.
• Building the governance-focused multi-agent platform TeamIntel (see AI reference projects).

Senior AI expert

Loom and Bloom

Python · TypeScript · n8n · Claude Code · Whisper · Gemini · Supabase · Notion · HubSpot · Digital Ocean

• Built an end-to-end content pipeline: one Loom video → marketing images, bilingual LinkedIn posts, newsletter and Help Center updates.
• n8n webhook → SSH → Claude Code session on a Digital Ocean VPS; three MCP servers (video, Notion, Supabase).
• Whisper word-level transcription, ffmpeg screenshots, Gemini UI annotation, PIL device mockups.
• Next.js upload UI plus a bilingual newsletter composer with HubSpot push.

• Led product & design (5 reports), hiring and development of team
• Implemented product squads, innovated around data ingestion and analysis.
• €0.5M to €4M ARR in 18 months

• Responsible for space & defence projects with NASA, ESA & national agencies
• Senior program management for special projects
• Collaboration with Thales and other key industry stakeholders

Development of AI-powered marketing and content workflows, concept development for scalable content processes, prompt engineering, and development of an AI-based text generator for scalable on-brand communication as well as creation of marketing and conversion copy.

• Strategic consulting and implementation of AI-supported automation solutions for service processes (email communication, document handling, review processing, voice agents)
• Technical orchestration through n8n (workflow automation), Claude and ChatGPT (LLMs), as well as custom API integrations into existing enterprise tools
• Measurable client results: reduced response times from hours to minutes, 8h/week less invoice processing, 75% fewer routine calls
• Classification of regulatory frameworks (GDPR, compliance) as part of client consulting
• Technical product ownership (backlog, roadmap, prioritization)
• Formal contract vehicle for freelance mandates, including 1&1 Telecommunications
• Setup & scaling of enterprise AI platforms