Techniques for performing conversation recovery of a system/user exchange are described. In response to determining that an action responsive to a user input cannot be performed, a system may determine a topic to recommend to a user. The topic may be unrelated to the original substance of the user input. The system may have access to various data representing a context in which a user provides an input to the system. The system may use these inputs and various data at runtime to make a determination regarding whether a user should be recommended a topic, as well as what that topic should be. The system may cause a question be output to the user, with the question asking the user about the topic, for example whether the user would like a song played, whether the user would like to hear information about a particular individual (e.g., artist), whether the user would like to know about a particular skill (e.g., a skill having a significantly high popularity among users of the system), or whether the user would like to know about some other topic. If the user responds affirmatively to the recommended topic, the system may pass the user experience off to an appropriate component of the system (e.g., one that is configured to perform an action related to the topic). If the user responds negatively, does not respond at all, or the system is unsure whether the user's response was affirmative or negative, the system may cease interaction with the user, thereby enabling the user to interact with the system as the user desires.