This paper will present a guiding framework and a multi-level taxonomy of automation levels specially adapted to Virtual Assistants in the context of HHI. This trust-based framework incorporates interaction phases, trust-affecting design principles, and design techniques. it also introduces a taxonomy of levels of autonomy explaining each level from a trust perspective. Based on the research insights, the author recommends designers to combine a holistic perspective on trust with contextual awareness, to be able to integrate the impact of contexts on interactions.