Generative and adaptive mediator for real-time interactions with conversational agents

A system comprising:

• one or more processors;
• and
• one or more computer-readable storage media having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the one or more processors, cause the one or more processors to:
• obtain a user communication indicative of a requested interaction by an auto-adaptive mediator engine and with a conversational agent of a target entity, wherein the requested interaction is performed on behalf of a user;
• obtain, from an artificial intelligence engine associated with the auto-adaptive mediator engine, a discovered intent corresponding to the requested interaction, wherein the discovered intent is an unknown intent for the auto-adaptive mediator engine;
• generate a sample dialog for the requested interaction based on the discovered intent and input requirements determined by the auto-adaptive mediator engine for the requested interaction, wherein the sample dialog is generated using a dialog generator;
• receive user feedback corresponding to action items and expected inputs identified from the sample dialog and output for user review by the auto-adaptive mediator engine;
• generate a dialog tree based on the sample dialog, the user feedback, and user-specific information extracted from the user communication, wherein the dialog tree uniquely corresponds to the user and the requested interaction with the conversational agent of the target entity;
• and
• use the auto-adaptive mediator engine and the generated dialog tree to automatically perform the requested interaction with the conversational agent of the target entity without receiving one or more user interventions during the requested interaction.

One or more non-transitory computer-readable media comprising computer-readable instructions, which when executed by one or more processors, cause the one or more processors to:

• obtain a user communication indicative of a requested interaction by an auto-adaptive mediator engine and with a conversational agent of a target entity, wherein the requested interaction is performed on behalf of the user;
• obtain, from an artificial intelligence engine associated with the auto-adaptive mediator engine, a discovered intent corresponding to the requested interaction, wherein the discovered intent is an unknown intent for the auto-adaptive mediator engine;
• generate a sample dialog for the requested interaction based on the discovered intent and input requirements determined by the auto-adaptive mediator engine for the requested interaction, wherein the sample dialog is generated using a dialog generator;
• receive user feedback corresponding to action items and expected inputs identified from the sample dialog and output for user review by the auto-adaptive mediator engine;
• generate a dialog tree based on the sample dialog, the user feedback, and user-specific information extracted from the user communication, wherein the dialog tree uniquely corresponds to the user and the requested interaction with the conversational agent of the target entity;
• and
• use the auto-adaptive mediator engine and the generated dialog tree to automatically perform the requested interaction with the conversational agent of the target entity without receiving one or more user interventions during the requested interaction.