More resources by this author

Rafał Łabędzki is a Senior AI Engineering Manager at deepsense.ai, where he leads the development of LLM/VLM evaluation frameworks and synthetic dataset production for enterprise AI deployment. He introduced the Business Utility metric, a risk-adjusted benchmark that combines analytical quality with repeatability, published in the May 2026 paper “Business Utility of Large Language Models as Exploratory Data Analysis Agents” (arXiv:2606.00051). His work spans agentic AI ROI frameworks, custom evaluation benchmarks, and production-ready model assessment across pharma, FMCG, manufacturing, and telecommunications. He holds a PhD in management and master’s degrees in finance and management from SGH Warsaw School of Economics, where his research focuses on human-AI collaboration in hybrid multi-agent systems. His career began in the video game industry in 2009.