In this compelling talk, Federico delves into the new challenges in software quality brought by the rise of Generative AI (GenAI) and Large Language Models (LLMs). As these advanced technologies become more integrated into applications, ensuring their quality presents unique hurdles. He explores the specific quality concerns associated with using LLMs, GenAI, and Retrieval-Augmented Generation (RAG), and discuss innovative testing approaches tailored to these systems. This session is designed to help you navigate these complexities, ensuring your applications not only meet but exceed quality standards.