Agentic. Done right.
I help companies build AI systems that work in the real world — not just in demos.
With deep expertise in document processing, computer vision, and agentic AI, I design and deliver solutions that automate complex workflows, extract intelligence from visual data, and let AI agents act autonomously and reliably.
Intelligent extraction, classification, and understanding of documents at scale. From invoices to technical drawings — structured data from unstructured sources.
Custom vision systems for quality inspection, object detection, and visual analytics. Production-grade models that perform under real-world conditions.
Autonomous AI agents that reason, plan, and execute multi-step workflows. From MCP integrations to full agentic pipelines — systems that take action, not just generate text.
I believe in building in the open. Selected projects:
Large language model hub library for unified LLM access
Teaching AI agents to build beautiful NiceGUI applications
Contributor to the Python web UI framework
MCP server for accessing enterprise news and events via AI agents
Image processing and visualization library for Python
Dynamic vision model hosting
Isolated Claude installation for continuous autonomous execution
Fast local and cloud-based file access and storage
Available for consulting, architecture reviews, and hands-on implementation.