This paper reports a case study on how explainability requirements were elicited during the development of an AI system for predicting cerebral palsy (CP) risk in infants. Over 18 months, we followed a development team and clinicians as they sought to design explanations that would make the AI system trustworthy. Contrary to the assumption that users need detailed explanations of the inner workings of AI systems, our findings show that clinicians trusted it when it enabled them to evaluate predictions against their own expertise. A simple prediction graph proved effective by supporting clinicians’ existing decision-making practices. Drawing on concepts from both Requirements Engineering and Explainable AI, we use the lens of Evaluative AI to introduce the notion of Evaluative Requirements: system requirements that allow users to scrutinize outputs on their own terms. The study demonstrates that such requirements are best discovered through iterative prototyping and observation, making them essential for building trustworthy AI systems in expert domains.