A system for integrating a telephone system and a computing system includes an interactive voice response (IVR) platform configured to: obtain a command based on an audio input from a user, determine a web application that corresponds to the command, determine a goal in the web application associated with the command, and obtain information indicating a shortest user interface path to the goal. The system includes a cobrowse client configured to receive a document object model (DOM) of a current state of the web application from a cobrowse session. The IVR platform is configured to, based on the DOM, determine a next user interface action along the shortest user interface path and generate a voice prompt for the user based on the next user interface action. The cobrowse client is configured to receive an updated DOM in response to execution by the user of the next user interface action.