Abstract: The present technology pertains to a system for generating automations based on a request/prompt from a user to a language model. The language model receives a prompt in a conversation thread with a user. When the prompt includes a request for a delayed action (i.e., an automation), the request is forwarded to an automations engine, which determines the delayed action from an action component of the request and a time at which to perform the delayed action from a temporal component of the request. A scheduling instruction based on the determined time is sent to a scheduler, which signals when the time occurs, triggering the automations engine to perform the delayed action, for example, by acting as the user's delegate and sending a delayed prompt to the language model to elicit a response and amending part or all of the resulting conversation to the conversation thread with the user.

Abstract: The present technology pertains to a system for using a temporal component in a prompt in a conversation thread between a user and a generative response system (the system) to determine when an event referenced in the prompt will occur. The event can be a delayed action of an automation request in the prompt. The temporal component is mapped to time-and-date value that is sent to a scheduler (e.g., a calendar application), which sends a notification when the time-and-date value occurs. Context provided by other parts of the conversation thread can resolve ambiguities in the temporal component. When the time-and-date value cannot be determined, the system can request additional temporal information or suggest an alternative temporal component for which a time-and-date value cannot be determined. Inquires to auxiliary (e.g. third-party) tools can be used to obtain information of other events on which the event is contingent.

Abstract: The present technology pertains to a generative response system that acts as a delegate of a user. In a conversation between the user and the system, the system receives a prompt from the user directing the system to perform an action as the delegate of the user. Further, the system receives one or more indicators that it is authorized to act as the user's delegate. For example, on the user's behalf, the system can act and represent the user in interactions with an external entity, such as an application, an API, or a third party. Additionally or alternatively, the system can include a generative response engine and a delegate engine, and the delegate engine can represent the user in a conversation with the generative response engine, in which conversation the delegate engine occupies the users role of generating prompts for conversational turns.

Abstract: The present technology pertains to a system for generating automations based on a request/prompt from a user to a language model. The language model receives a prompt in a conversation thread with a user. When the prompt includes a request for a delayed action (i.e., an automation), the request is forwarded to an automations engine, which determines the delayed action from an action component of the request and a time at which to perform the delayed action from a temporal component of the request. A scheduling instruction based on the determined time is sent to a scheduler, which signals when the time occurs, triggering the automations engine to perform the delayed action, for example, by acting as the user's delegate and sending a delayed prompt to the language model to elicit a response and amending part or all of the resulting conversation to the conversation thread with the user.

Abstract: Methods and systems for monitoring and managing healthcare performance. The system comprises one or more network interfaces configured to provide access to a network and one or more data processing servers coupled to the one or more network interfaces to enable communication with one or more healthcare manager devices. The one or more data processing servers to execute instructions to receive healthcare data from a plurality of data source devices over the network, extract patient medical data from the received healthcare data, group the patient medical data according to episodes of care, analyze the patient medical data to determine variances, generate prescriptive opportunity scripts to reduce the determined variances, add the prescriptive opportunity scripts to a playbook, and generate output corresponding to the analysis and the playbook to the one or more healthcare manager devices.