Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: In one embodiment, a method includes receiving a first input by a user from a client system associated with the user, wherein the first input is in a voice modality, analyzing the first input to generate one or more candidate hypotheses, determining one or more modalities for presenting output generated by the one or more computing systems to the user at the client system, and sending instructions to the client system for presenting one or more suggested auto-completions corresponding to one or more of the candidate hypotheses, respectively, wherein each suggested auto-completion comprises the corresponding candidate hypothesis, and wherein the one or more suggested auto-completions are presented in the one or more determined modalities.

Abstract: Disclosed are various embodiments for routing communications to service agents based on a workflow. A computing device identifies a user intent object corresponding to a user interaction with the computing device. The computing device then generates a search criterion based on the identified user intent object and uses the search criterion for identifying the user intent in subsequent user interactions. After identifying the user intent, the computing device can identify a workflow corresponding to the user intent object. Later, the computing device can process one or more tasks associated with the workflow.

Abstract: Disclosed are various embodiments for routing communications to service agents based on a workflow. A computing device identifies a user intent object corresponding to a user interaction with the computing device. The computing device then identifies a workflow corresponding to the user intent object. Later, the computing device identifies a service agent capable of completing the workflow. Then, the computing device routes a user to the service agent.

Abstract: Techniques are provided for presenting and dynamically updating a user interface that represents features/services associated with a service provider. For example, a user interface element associated with services offered by a service provider may be maintained. Further, instructions to present the user interface element with at least a first portion that represents a service of the services that is accessible may be provided. Information corresponding to an interaction with the service provider may be received. A second portion of the user interface element to present may be determined based at least in part on the received information and aggregate user data that identifies interactions by a plurality of users with the services offered by the service provider. Instructions may be provided to present the user interface element with the first portion and the determined second portion.

Abstract: Disclosed are various embodiments for an automated service agent. Natural language inputs are obtained from a client. The natural language inputs and other data are input to machine learning models to identify intents reflected in the natural language inputs. A state in a workflow is updated to reflect the identified intents. Responses may be communicated to the client to further progress in the workflow.