Abstract: Systems and methods provide for structured prompts that are accessible through application programming interface (API.) An API request that includes one or more data elements and is indicative of a pre-defined prompt template for executing a task is received from an application process. In response, a pre-defined prompt template indicated by the API request is obtained. A prompt is generated for a machine learning model by applying the one or more data elements to the pre-defined prompt template. The prompt is provided to the machine learning model and the machine learning model processes the prompt to generate an output. The output is then transmitted back to the application process as an API response.

Abstract: The subject technology provides for a model management and deployment system for machine learning models. A system includes a model manager configured to schedule execution of one or more machine learning models on one or more electronic devices or servers. The system also includes a model catalog configured to store information associated with the one or more machine learning models. The model manager may access the model catalog to determine scheduling priorities based on the stored information.

Abstract: Some techniques are described herein for tracking items across different devices. Such techniques synchronize a portion of each item while locally storing another portion. In some examples, the synchronization is performed via a conflict-free replicated data type (CRDT) and includes exchanging state vectors and/or hashes corresponding to portions of items that are being synchronized. Other techniques incrementally update local views of data as new data is received. Such techniques use storage plans that maintain operations for different local views. Other techniques manage the order of updates of different local views of data using various sets of criteria described herein. For example, some views can intentionally be left out of date while other views can be updated more frequently to satisfy requests for such views.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: One embodiment provides for an electronic device, comprising a non-transitory machine-readable medium to store instructions, one or more processors to execute the instructions, and a memory coupled to the one or more processors. The memory can be configured to store a set of synchronization data associated with interaction between the electronic device and one or more applications and instructions which, when executed by the one or more processors, configure the one or more processors to retrieve a set of synchronization data to be transmitted from the electronic device to select a transport channel from one of a peer-to-peer channel or a network-based channel and transmit the set of synchronization data from the electronic device to one or more remote devices via the selected transport channel.

Abstract: One embodiment provides for an electronic device, comprising a non-transitory machine-readable medium to store instructions, one or more processors to execute the instructions, and a memory coupled to the one or more processors. The memory can be configured to store a set of synchronization data associated with interaction between the electronic device and one or more applications and instructions which, when executed by the one or more processors, configure the one or more processors to retrieve a set of synchronization data to be transmitted from the electronic device to select a transport channel from one of a peer-to-peer channel or a network-based channel and transmit the set of synchronization data from the electronic device to one or more remote devices via the selected transport channel.

Abstract: Content objects may be selected for sharing and shared across devices using a sharing routine and suggestion engine to provide suggestions of target applications to share the content objects and recipients with whom the content objects may be shared. A sharing routine may receive and analyze a sharing request and invoke a suggestion engine configured to generate application suggestions and/or recipient suggestions. The sharing routine may receive sets of application suggestions and/or recipient suggestions from a suggestion engine, modify and/or select subsets of the suggestions to be provided to user via a sharing user interface. In response to a user selection of applications and/or recipient via the user interface, the sharing routine may invoke the selected application for sharing, and provide the content object to the selected application.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: Systems and methods can suggest applications and/or recipients for a user of a computing device to perform communication. The suggestions can be provided on a user interface for a user to select. A suggestion engine can use historical user interactions that include a recipient, a communication application used to communicate with the recipient, and contextual data to determine which application and/or recipients to suggest. The user interactions may occur in a variety of ways, e.g., after a content object has been selected within a host application, where a communication application is selected thereafter. Multiple models may be used to provide the suggestions, such as a pattern model or a cluster model that uses recent user interactions. As another example, a heuristics model may also be used.

Abstract: The subject technology provides systems and methods for context-based user status indicator selection. In an example, a method includes obtaining, by a first electronic device associated with a first user, status indicators, each of which indicates a respective status of a second user of a second electronic device. Furthermore, the method includes determining, by the first electronic device, a respective relevance priority of each of the status indicators. Based on the determined respective priorities, a subset of the status indicators is selected by the first electronic device and is displayed in a graphical element on the first electronic device.

Abstract: Techniques are disclosed for predictive media streaming using microlocation. Microlocations of a mobile device can be determined by measuring one or more sensor values at one or more times, the one or more sensor values are determined from one or more signals emitted by a corresponding one or more signal sources. Streaming events can be stored at the mobile device. Each streaming event may include a destination device for playing media and a cluster location, the cluster location corresponding to sensor values that are spatially near each other. A selection of a media item is detected and one or more current sensor values are measured. A current cluster location can be identified using the one or more current sensor value. The current cluster location and the streaming events can identify a particular destination device for playing the selected media item.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: Techniques are disclosed for predictive media streaming using microlocation. Microlocations of a mobile device can be determined by measuring one or more sensor values at one or more times, the one or more sensor values are determined from one or more signals emitted by a corresponding one or more signal sources. Streaming events can be stored at the mobile device. Each streaming event may include a destination device for playing media and a cluster location, the cluster location corresponding to sensor values that are spatially near each other. A selection of a media item is detected and one or more current sensor values are measured. A current cluster location can be identified using the one or more current sensor value. The current cluster location and the streaming events can identify a particular destination device for playing the selected media item.

Abstract: Techniques are disclosed for predictive media streaming using microlocation. Microlocations of a mobile device can be determined by measuring one or more sensor values at one or more times, the one or more sensor values are determined from one or more signals emitted by a corresponding one or more signal sources. Streaming events can be stored at the mobile device. Each streaming event may include a destination device for playing media and a cluster location, the cluster location corresponding to sensor values that are spatially near each other. A selection of a media item is detected and one or more current sensor values are measured. A current cluster location can be identified using the one or more current sensor value. The current cluster location and the streaming events can identify a particular destination device for playing the selected media item.

Abstract: Content objects may be selected for sharing and shared across devices using a sharing routine and suggestion engine to provide suggestions of target applications to share the content objects and recipients with whom the content objects may be shared. A sharing routine may receive and analyze a sharing request and invoke a suggestion engine configured to generate application suggestions and/or recipient suggestions. The sharing routine may receive sets of application suggestions and/or recipient suggestions from a suggestion engine, modify and/or select subsets of the suggestions to be provided to user via a sharing user interface. In response to a user selection of applications and/or recipient via the user interface, the sharing routine may invoke the selected application for sharing, and provide the content object to the selected application.

Abstract: Systems and methods can suggest applications and/or recipients for a user of a computing device to perform communication. The suggestions can be provided on a user interface for a user to select. A suggestion engine can use historical user interactions that include a recipient, a communication application used to communicate with the recipient, and contextual data to determine which application and/or recipients to suggest. The user interactions may occur in a variety of ways, e.g., after a content object has been selected within a host application, where a communication application is selected thereafter. Multiple models may be used to provide the suggestions, such as a pattern model or a cluster model that uses recent user interactions. As another example, a heuristics model may also be used.

Abstract: Systems and processes for user configurable task triggers are provided. In one example, at least one user input, including a selection of at least one condition of a plurality of conditions and a selection of at least one task of a plurality of tasks, is received. Stored context data corresponding to an electronic device is received. A determination is whether the stored context data indicates an occurrence of the at least one selected condition. In response to determining that the stored context data indicates an occurrence of the at least one selected condition, the at least one selected task associated with the at least one selected condition is performed.

Abstract: Techniques are disclosed for predictive media streaming using microlocation. Microlocations of a mobile device can be determined by measuring one or more sensor values at one or more times, the one or more sensor values are determined from one or more signals emitted by a corresponding one or more signal sources. Streaming events can be stored at the mobile device. Each streaming event may include a destination device for playing media and a cluster location, the cluster location corresponding to sensor values that are spatially near each other. A selection of a media item is detected and one or more current sensor values are measured. A current cluster location can be identified using the one or more current sensor value. The current cluster location and the streaming events can identify a particular destination device for playing the selected media item.