Deploying agentic AI: what worked, what broke, and what we learned

When Agentic AI started dominating research papers, demos, and conference talks, I was curious but cautious. The idea of intelligent agents, autonomous systems powered by large language models that can plan, reason, and take actions using tools, sounded brilliant in theory. But I wanted to know what happened when you used them. Not in a toy notebook or a slick demo, but in real projects, with real constraints, where things needed to work reliably and repeatably. In my role as Clinical AI & Data Scientist at Bayezian Limited, I work at the intersection of data science, statistical modelling, and clinical AI governance, with a strong emphasis on regulatory-aligned standards such as CDISC. I have been directly involved in deploying agentic systems into environments where trust and reproducibility are not optional. These include real-time protocol compliance, CDISC mapping, and regulatory workflows. We gave agents real jobs. We let them loose on messy documents. And then we watched them work, fail, learn, and (sometimes) recover. This article is not a critique of Agentic AI as a concept.