A multi-modal call is accepted from a caller through a telephony interface, which accommodates multi-modal calls including at least one of verbal speech and text messaging. Incoming speech in the multi-modal call is converted into transcribed text. Incoming text messaging is matched with the transcribed text. The multi-modal call is automatically assigned through a session manager to a session under operation of a live agent. The transcribed text and incoming text messaging are progressively processed during the session through an agent application by performing a customer support scenario interactively monitored and controlled by the live agent.