PhD. AI transformation executive and independent researcher at ARSENTEV.AI (https://arsentev.ai), Barcelona. I run dozens of autonomous LLM agents in production and publish empirical measurements of what drives their cost and reliability: inference economics, prompt-cache behaviour, context management and reproducible measurement methodology for agentic systems. Datasets and replication material are open; research index at https://arsentev.ai/research. Author of an IETF Internet-Draft on agent run metadata. My doctoral work covers health informatics, digital health and epidemiology, which is the bridge I keep between clinical evidence standards and AI evaluation. ORCID 0000-0002-9120-7298.