As wireless devices continue to become more prevalent, heterogeneous wireless networks - in which communicating devices have at their disposal multiple types of radios - will become the norm. Communication between nodes in these networks ought to be as simple as possible; they should be able to seamlessly switch between different radios and network stacks on the fly in order to better serve the user. To make this a possibility, we consider the challenging problems of when two communicating devices should decide to switch to a different radio, and which radio they should choose. We design an autonomous and intelligent radio switch (AIRS) decision algorithm that uses predicted radio availability and user profiles to choose the best available radio for two adjacent devices. The decision algorithm uses several parameters to avoid switching radios too frequently. We use a simulation study to evaluate the best settings for several parameters, then show that the AIRS system performs better than several alternative algorithms. AIRS is able to provide dynamic, but stable radio switching, while balancing the competing objectives of high throughput and low power consumption.