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 can integrate a generative response engine capable of dynamically determining and displaying generated content in appropriate user interface formats. In response to user prompts, the generative response engine can display content in a content frame separate from the traditional conversational interface. The system intelligently assesses the nature of the content and determines the most suitable display mode, enhancing user interaction and collaboration. This interface facilitates both content creation and user collaboration by enabling seamless transitions between conversational responses and rich media content, such as drawings, games, or documents. The system thus optimizes content interaction based on its type and user needs, supporting diverse use cases across media formats.

Abstract: The present technology can integrate a generative response engine capable of dynamically determining and displaying generated content in appropriate user interface formats. In response to user prompts, the generative response engine can display content in a content frame separate from the traditional conversational interface. The system intelligently assesses the nature of the content and determines the most suitable display mode, enhancing user interaction and collaboration. This interface facilitates both content creation and user collaboration by enabling seamless transitions between conversational responses and rich media content, such as drawings, games, or documents. The system thus optimizes content interaction based on its type and user needs, supporting diverse use cases across media formats.

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: While AI models, like large language models, are powerful tools with multiple applications, they can be complex to use and can require a lot of resources to operate. The disclosed systems and methods provide tools to generate customized models (or AI agents) that are configured with features like tailored knowledge, capabilities, and instructions that make them faster, more efficient, and use less computational resources. AI agents may offer several technical advantages of improved efficiency, resource use, and connectivity. This disclosure describes systems and methods to configure, evaluate, generate, and deploy the custom models that can more efficiently run specific tasks. Disclosed systems and methods are configured to, for example, receive a query to generate a custom model, generate the AI agent custom model with the information in the query, and then resolve user queries more efficiently using the custom model.

Abstract: While AI models, like large language models, are powerful tools with multiple applications, they can be complex to use and can require a lot of resources to operate. The disclosed systems and methods provide tools to generate customized models (or AI agents) that are configured with features like tailored knowledge, capabilities, and instructions that make them faster, more efficient, and use less computational resources. AI agents may offer several technical advantages of improved efficiency, resource use, and connectivity. This disclosure describes systems and methods to configure, evaluate, generate, and deploy the custom models that can more efficiently run specific tasks. Disclosed systems and methods are configured to, for example, receive a query to generate a custom model, generate the AI agent custom model with the information in the query, and then resolve user queries more efficiently using the custom model.

Abstract: While AI models, like large language models, are powerful tools with multiple applications, they can be complex to use and can require a lot of resources to operate. The disclosed systems and methods provide tools to generate customized models (or AI agents) that are configured with features like tailored knowledge, capabilities, and instructions that make them faster, more efficient, and use less computational resources. AI agents may offer several technical advantages of improved efficiency, resource use, and connectivity. This disclosure describes systems and methods to configure, evaluate, generate, and deploy the custom models that can more efficiently run specific tasks. Disclosed systems and methods are configured to, for example, receive a query to generate a custom model, generate the AI agent custom model with the information in the query, and then resolve user queries more efficiently using the custom model.

Abstract: While AI models, like large language models, are powerful tools with multiple applications, they can be complex to use and can require a lot of resources to operate. The disclosed systems and methods provide tools to generate customized models (or AI agents) that are configured with features like tailored knowledge, capabilities, and instructions that make them faster, more efficient, and use less computational resources. AI agents may offer several technical advantages of improved efficiency, resource use, and connectivity. This disclosure describes systems and methods to configure, evaluate, generate, and deploy the custom models that can more efficiently run specific tasks. Disclosed systems and methods are configured to, for example, receive a query to generate a custom model, generate the AI agent custom model with the information in the query, and then resolve user queries more efficiently using the custom model.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A selection of a time-lapse amount can be received. A subset of frames from the original set of frames can be identified based on the time-lapse amount. An orientation-based image stabilization process can be applied to the subset of frames to produce a stabilized subset of frames. A stabilized time-lapse media content item can be provided based on the stabilized subset of frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A selection of a time-lapse amount can be received. A subset of frames from the original set of frames can be identified based on the time-lapse amount. An orientation-based image stabilization process can be applied to the subset of frames to produce a stabilized subset of frames. A stabilized time-lapse media content item can be provided based on the stabilized subset of frames.

Abstract: Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. Motion data associated with the original set of frames can be acquired. A motion pattern can be determined based on the motion data. A subset of frames that are associated with the motion pattern can be identified out of the original set. A time-lapse media content item can be provided based on the subset of frames that are associated with the motion pattern.

Abstract: Highlights from a community of users highlighting portions of an electronic digital work may produce aggregated highlights. Users may have access to public and purchase versions of the aggregated highlights. Reconciliation of highlights across multiple versions of the same digital work may also take place, with the reconciled highlights incorporated into the aggregated highlights.