Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an Interaction Engine. According to various embodiments, the Interaction Engine generates, within a unified three-dimensional (3D) coordinate space: a virtual 3D medical model positioned according to a current model pose and at least one a virtual 3D hand representation. The Interaction Engine renders an AR display that includes display of the virtual 3D medical model positioned according to the current model pose and the virtual 3D hand representation. The Interaction Engine identifies selection of a slate virtual interaction based on the type of movement of the virtual 3D hand representation. The Interaction Engine modifies the AR display by rendering a virtual slate concurrently displayed with the virtual 3D medical model. The Interaction Engine adjusts the display of the virtual 3D medical model based at least on subsequent physical gestures with respect to the virtual slate.