Despite significant advancements, many AI systems in the medical domain function as passive tools rather than trusted collaborators in hybrid human-AI settings. Their lack of adaptability, explainability, and communication efficiency hinders their potential to become trusted diagnostic companions. We developed a framework that supports hybrid decision-making in medical dermatopathology. It mirrors real-life consultations between medical professionals, where diagnostic indicators for ambiguous regions often hinge on neighbouring cells and facilitates a two-way communication channel, enabling an AI agent and a doctor to exchange observations with justifications when classifying ambiguous cells in histological tissue samples. Central to our research is the integration of computational Theory of Mind enabling the agent to infer the doctor’s reasoning and establishing common ground during their interaction. This strengthens the efficiency of communication and trust in human-AI collaboration.