Creator of n8n-mcp — the open-source tool AI agents use to build n8n automations. 108,000+ engineers, 22,000+ GitHub stars, used by teams at Deutsche Telekom, PayPal, Intercom, MIT and NYU.
I build production AI systems for companies. Not slide decks, not demos that stall after the pilot. Systems that run in production and stay maintained: 750+ workflows delivered across multiple companies in 5 industries. I work directly with the people who do the work, so the system that ships is one they already use.
What I build:
- Agentic process automation — n8n workflows with AI agents, plus custom microservices (APIs, scrapers, document converters) where low-code ends.
- Document intelligence & RAG — hundreds of thousands of PDFs, scans and mixed formats turned into a knowledge base searchable by people and AI agents.
- Agentic software development — full applications and backends built with Claude Code + MCP, under the discipline of architecture, specs, tests and multi-agent CI.
- MCP servers, fine-tuning & AI architecture — custom MCP servers, model selection, fine-tuned models where general models fail, with security and cost control built in.
How I work: fixed price for setup, monthly retainer for maintenance and new automations. You buy outcomes, not hours.
Industries served: e-commerce, legal & tax, professional services, healthcare, digital advertising. Previously Head of AI at Boldare and current IT/AI advisor to the World Bank Group.
If you want to move from AI experiments to systems that run your operations, let's talk. cal.com/czlonkowski/30min