Explore the critical aspects of machine learning model trustworthiness in this 39-minute conference talk from MLOps World: Machine Learning in Production. Delve into the challenges posed by increasingly complex ML models and architectures, and learn how automated evaluations can ensure the reliability of model predictions. Discover the key pillars of AI quality, their significance, and effective evaluation methods. Gain insights from María Grandury, an ML Research Engineer at nuerocat GmbH, as she shares her expertise in AI robustness and explainability. Understand the importance of delivering high-quality models in terms of performance, robustness, and explainability to meet client expectations and maintain trust in AI systems.