Abstract: Methods, systems and computer program products for analyzing historical user interactions across multiple users within a content management system. This approach employs machine learning to identify patterns and similarities in user behavior, enabling more accurate AI agent assignment and customization. By considering the collective behavior of user groups, the invention can provide AI agents that are better tailored to specific tasks and user needs, ultimately improving their effectiveness and user satisfaction.

Abstract: Methods, systems and computer program products for analyzing historical user interactions across multiple users within a content management system. This approach employs machine learning to identify patterns and similarities in user behavior, enabling more accurate AI agent assignment and customization. By considering the collective behavior of user groups, the invention can provide AI agents that are better tailored to specific tasks and user needs, ultimately improving their effectiveness and user satisfaction.

Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

Abstract: Methods, systems, and computer program products for collaboration systems. A method for identifying selected portions of a set of content objects for use in generating a large language model (LLM) prompt comprises: identifying a content management system (CMS) wherein collaboration activities occur over time and over content objects maintained in the CMS, and wherein the CMS maintains a historical record of occurrences of the collaborator activities over the content objects. Upon receiving a natural language query from a CMS collaborator, reducing a larger corpus of content objects to a smaller corpus of context passages that are used in an LLM prompt. The smaller corpus of passages is formed using a two-phase reduction scheme whereby firstly, selected constituents from the larger corpus of content objects are identified based on CMS metadata; and then, rather than considering the larger corpus, instead considering only the selected constituents when generating the LLM prompt.

Abstract: Disclosed is an improved approach to implement metadata extraction, to extract metadata that can be used for metadata queries. The query may be applied against metadata extracted from content stored in a cloud-based content management system.

Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

Abstract: A method for processing content management system workflows. Systems and subsystems are established for configuring a content management system to implement workflow processes wherein the content management system (CMS) exposes instances of stored content objects to a plurality of user devices through an electronic interface. Further systems and subsystem are established for identifying metadata maintained by the CMS for the stored content objects, and for identifying a generative AI entity (GAIE) to interact with the CMS. On an ongoing basis, the foregoing systems and subsystems carry out steps for (1) forming a GAIE prompt, wherein the GAIE prompt comprises at least a portion of the metadata identified from the CMS for the stored content objects, (2) receiving a response from the GAIE, wherein the response corresponds to the GAIE prompt; and (3) using, by the CMS, the response from the GAIE to implement processing of a content management system workflow.

Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

Abstract: A recommendation system integrated with a content management system (CMS). The CMS stores instances of shared content objects and coordinates user interactions by and between a plurality of CMS users. Shared content objects are divided into a plurality of portions, after which any user interactions over the various portions of the content object are observed and analyzed. User interest inferences are drawn from analysis of the observed user interactions taken user over respective particular portions of the content object. Based on the inferred user interests, fine-grained recommendations are formed and propagated. Some fine-grained recommendations refer to further content objects (e.g., content objects of different types). Some fine-grained recommendations are propagated to other CMS users (e.g., to a plurality of CMS users that are related in some way). The fine-grained recommendations refer to one or more specific portions of a content object as well as to the content object itself.

Abstract: Systems and methods for deploying data processing services to operate with a cloud-based collaboration platform. Deployment of a data processing service commences upon receiving a description of a function to perform on content of the cloud-based collaboration platform. The description comprises characteristics of the function as well as characteristics of given input and characteristics of desired output. A data processing service is formed (e.g., compiled) into a collection of executable instructions that communicate with an integration layer of the cloud-based collaboration platform. The data processing service is configured to receive event data indicative of an event pertaining to a content item stored in the cloud-based collaboration platform, and to then process the event data to determine at least one aspect of the input and at least one aspect of the output. The portion of the executable instructions comprising the function are executed on the content item to produce desired output.

Abstract: Shared content is stored at a cloud-based collaboration platform hosted at first network domain. External data processing services are hosted at a second domain. An integration layer situated between the cloud-based collaboration platform and the external data processing services is configured to receive triggering events pertaining to content of the cloud-based collaboration platform. Based on characteristics of the content, communications with the external data processing services are initiated. The communication includes accessing network interfaces to send and receive data between the network domain of the cloud-based collaboration platform and a different network domain of the external data processing services. A plurality of rules are applied to select between a first external data processing service at a first network domain and a second external data processing service at a second domain.

Abstract: Systems for fine-grained management of plug-ins. A method embodiment commences upon identifying a plug-in to perform a particular computing function in a computing environment. A set of configuration parameters that correspond to the particular computing function are determined. Based at least in part on the determined configuration parameters, an instance-specific plug-in management wrapper corresponding is generated. The instance-specific plug-in management wrapper includes fine-grained management controls so as to be able to observe performance characteristics, functional characteristics and other runtime characteristics of the plug-in while it operates in the computing system. When a particular plug-in is invoked, its management wrapper is automatically generated so as to encapsulate the particular plug-in. Deployment instructions are generated to instantiate the plug-in management wrapper and its encapsulated plug-in in the computing system.

Abstract: Systems and methods for combining two or more outputs of two or more data processing services. A method embodiment commences upon receiving an event indication and a content item from a cloud-based collaboration platform. The method analyzes the event and the content item to determine two or more data processing services to apply to the content item. The method further determines a common metric to use to correlate two or more different outputs from the two or more data processing services. The method invokes both of the two or more data processing services, which in turn each generate respective outputs. Metadata that relates the respective outputs based on the common metric as well as the outputs themselves are stored for retrieval by the cloud-based collaboration platform. A query is executed to retrieve at least portions of the respective outputs and corresponding metadata. The retrieved data is correlated in a display.

Abstract: Methods, systems and computer program products for managing content objects in a content management system. A metadata template is assigned to a content object of the content management system. Extensible metadata pertaining to the content object is allocated in accordance with the assigned metadata template. Various operations over the content object result in population of the allocated extensible metadata. When the content object is subjected to a workflow, the execution flow and/or the form of responses associated with execution of the workflow are informed by the populated extensible metadata. A single content object can take on an association with multiple sets of extensible metadata and each set of extensible metadata can take on association with a respective workflow.

Abstract: Systems and corresponding computer-implemented methods for context-based rule evaluation in an electronic data storage system are described. A request to perform an operation with respect to a resource is received from a client device, with the request including various attributes associated with the client device. At least one set of rules applicable to the operation is identified. The rules can be formed from a combination of primitives arranged to dynamically evaluate attributes associated with the resource and attributes associated with the client device. Based on the evaluation of the rule set(s), an action is identified to be performed with respect to the resource.

Abstract: Systems and methods for deploying data processing services to operate with a cloud-based collaboration platform. Deployment of a data processing service commences upon receiving a description of a function to perform on content of the cloud-based collaboration platform. The description comprises characteristics of the function as well as characteristics of given input and characteristics of desired output. A data processing service is formed (e.g., compiled) into a collection of executable instructions that communicate with an integration layer of the cloud-based collaboration platform. The data processing service is configured to receive event data indicative of an event pertaining to a content item stored in the cloud-based collaboration platform, and to then process the event data to determine at least one aspect of the input and at least one aspect of the output. The portion of the executable instructions comprising the function are executed on the content item to produce desired output.

Abstract: Systems and methods for combining two or more outputs of two or more data processing services. A method embodiment commences upon receiving an event indication and a content item from a cloud-based collaboration platform. The method analyzes the event and the content item to determine two or more data processing services to apply to the content item. The method further determines a common metric to use to correlate two or more different outputs from the two or more data processing services. The method invokes both of the two or more data processing services, which in turn each generate respective outputs. Metadata that relates the respective outputs based on the common metric as well as the outputs themselves are stored for retrieval by the cloud-based collaboration platform. A query is executed to retrieve at least portions of the respective outputs and corresponding metadata. The retrieved data is correlated in a display.

Abstract: Shared content is stored at a cloud-based collaboration platform hosted at first network domain. External data processing services are hosted at a second domain. An integration layer situated between the cloud-based collaboration platform and the external data processing services is configured to receive triggering events pertaining to content of the cloud-based collaboration platform. Based on characteristics of the content, communications with the external data processing services are initiated. The communication includes accessing network interfaces to send and receive data between the network domain of the cloud-based collaboration platform and a different network domain of the external data processing services. A plurality of rules are applied to select between a first external data processing service at a first network domain and a second external data processing service at a second domain.

Abstract: Systems for fine-grained management of plug-ins. A method embodiment commences upon identifying a plug-in to perform a particular computing function in a computing environment. A set of configuration parameters that correspond to the particular computing function are determined. Based at least in part on the determined configuration parameters, an instance-specific plug-in management wrapper corresponding is generated. The instance-specific plug-in management wrapper includes fine-grained management controls so as to be able to observe performance characteristics, functional characteristics and other runtime characteristics of the plug-in while it operates in the computing system. When a particular plug-in is invoked, its management wrapper is automatically generated so as to encapsulate the particular plug-in. Deployment instructions are generated to instantiate the plug-in management wrapper and its encapsulated plug-in in the computing system.