IT Consultant · AI & Agentic Engineering · Dresden, Germany
I build AI agents that run in production — not just prototypes.
From LLM orchestration and fullstack web apps to secure infrastructure, with an enterprise IT background.
- AI agents in production — Design, build, and operate autonomous agents with semantic memory, multi-LLM routing, and real-time monitoring
- Fullstack web applications — Next.js / React / TypeScript frontend, Python / FastAPI backend, Supabase / PostgreSQL data layer
- AI workflow architecture — Context engineering, prompt design, and structured agentic workflows that deliver reproducible results
- Automation & data pipelines — Web scraping, NLP preprocessing, n8n workflows, Docker deployments, CI/CD pipelines
- Enterprise governance — Security-first architecture and operational discipline from years of Microsoft Cloud consulting
- 🦞 Vega — AI assistant on OpenClaw running 24/7 on a Tailscale-isolated VPS — handles research, task delegation, automated security audits, and daily operations via Telegram
- 📡 project-beat — Automated freelance project discovery for the German IT market — scrapes 5 platforms 2x daily, deduplicates via fuzzy + embedding similarity, ranks with hybrid NLP/semantic scoring (v1.2 live)
- 🖥️ Mission-Control — Operations dashboard that gives full visibility into agent state, task pipelines, server health, and deployment status — one tab instead of five terminals
- 🛡️ ShieldClaw — Open-source prompt injection defense (71 patterns, 4 active hooks, zero token overhead) that protects AI agents from adversarial inputs in production
- 🔧 OpenClaw Skills — Reusable agent capabilities for the OpenClaw ecosystem
- 🔨 SkillForge — Self-evolving skill engine for Claude Code — text gradients for directed fixes, multi-skill mesh conflict detection, meta-learning data flywheel, failure triage. Your 50th skill ships in half the iterations of your 1st (v4.0, 99.4/100 structural score, 51 tests)
Structured workflows ensure AI-driven development produces reliable, auditable results — not guesswork.
| Practice | What it means |
|---|---|
| Phase-based execution | Planning, implementation, verification with atomic commits and parallel subagents |
| Context engineering | Token-optimized instruction files, progressive skill loading, scoped rules per project |
| Hook-based guardrails | Security enforcement at zero token cost via PreToolUse/PostToolUse hooks |
| Semantic memory | Vector search over agent history with automatic re-embedding for persistent context |
| Tool | Role |
|---|---|
| Ghostty | Custom-configured terminal with splitscreen layout |
| lazygit | TUI Git client — keyboard-driven version control |
| Wispr Flow | Voice-to-text AI — speak commands, code and prompts |
| Claude Code | Agentic IDE running in the adjacent pane |
| VS Code / Cursor / Antigravity | IDEs for visual editing, debugging, and AI-assisted coding |
| Git Worktrees | Parallel branch development without context switching |
Claude Code Ecosystem
My agentic development workflow runs on Claude Code with a curated set of plugins, frameworks, and custom skills — from structured planning to autonomous code review and security enforcement.
Official Plugins
Community Frameworks
Custom Skills
| Repo | Description |
|---|---|
| 🖥️ openclaw-mission-control | Operations dashboard for AI agent infrastructure — Kanban, live status, task delegation, monitoring |
| 🛡️ openclaw-skill-shieldclaw | Prompt injection defense for AI agents — 71 patterns, 133 tests, MIT licensed |
| 🔨 skillforge | Self-evolving skill engine — text gradients, skill mesh, meta-learning, failure triage. Autoresearch loop meets compounding intelligence (v4.0) |
I spent years in Microsoft Cloud consulting — deploying M365 environments, managing tenant security, and building automation for enterprise clients. That experience shapes how I approach AI engineering: production-grade infrastructure, security by default, and operational discipline over hype.
More recently, I've built automated data pipelines with German-language NLP — compound splitting, semantic matching, and embedding-based deduplication for production use cases.
Today I focus on AI agents and agentic systems. I build agents that run unattended in production, not demos that break after the first edge case. The enterprise mindset is the differentiator — I think in terms of uptime, audit trails, and access control, not just prompt quality.
Available for freelance and consulting projects in AI agent development, fullstack web applications, NLP/ML systems, and automation.