This work tackles the problem of building trustworthy AI for the automotive industry in a context in which generic guidelines have already been proposed yet their instantiation is far from straightforward. The following work presents a first iteration of a methodology for developing trustworthy AI in CCAM (Connected, Cooperative Autonomous Mobility) applications as a meet-in-the-middle approach integrating generic European ethics guidelines (top-down) as well as leveraging the scenario approach (bottom-up) as a well-known practice in the automotive field. The result is a first version of application of the trustworthiness criteria into a use case of AI-enhanced ADAS and a related scenario subset. The premise is that in order to truly develop trustworthy AI, trustworthiness criteria are necessary but must be coupled with solid practices in the field and systems of reference in order to ensure integration of ongoing and proven engineering processes to the new challenges and opportunities linked to the development cycle of AI-based systems.