Abstract: Disclosed herein are system, method, and computer program product aspects for automatically generating recommended actions for a user. During operation, many different data points are examined, including user actions, calendar data, company guidelines, etc. A machine-learning model is used to analyze these data points and determine any number of recommended actions for the users. Such actions may include any known actions to be carried out in the course of the user’s business, such as following up with a customer, drafting an introductory email, submitting expense reports, etc. Once the recommended actions have been identified, they are provided to the user in a chat interface or list interface, where the user can view, select, edit, or authorize such actions. The model can then execute authorized actions as needed.

Abstract: An interactive agent (e.g., a chatbot, an artificially intelligent assistant, a digital assistant, etc.) may utilize a dynamic button of a user interface to output a request suggestion the user can request while conversing with the interactive agent. The interactive agent may utilize personal account and interaction history in order to provide relevant request suggestions that the interactive agent can provide a response to when the dynamic button is selected. The dynamic buttons may be dynamically updated as the conversation progresses between the interactive agent and the user in order to provide relevant request suggestions to the user based on the conversation.

Abstract: An interactive agent may utilize a dynamic feed of a user interface to output an indication of a first data object in a first format based on a natural language request from a user device for the first data object. Based on an indication that the request for the first data object is associated with a user profile and an interaction with the indication of the first data object, modification data that indicates a modification for the first format may be mapped to the user profile. The interactive agent may modify a second format for an indication of a second data object to match the modification of the first format for the first data object based on the modification data and a natural language request for the second data object. The dynamic feed may output an indication of the second data object in the modified second format.

Abstract: Disclosed herein are system, method, and computer program product embodiments for an improved integrated AI assistant. The integrated AI assistant performs a plurality of tasks within a host system including providing predictive action suggestions, generating clickable results, updating objects, searching fields, updating fields, determining the AI-generated content within a field, providing chat histories, and providing citations.