Abstract: Systems and techniques for conversational composite action execution are described herein. Natural language workflow descriptions are received from expert users, the descriptions are processed using language models to identify action sequences, and directed acyclic graphs (DAGs) are generated that represent workflows by mapping actions to automated agents. These DAGs are stored as composite action recipes in a vector database. End users can then submit natural language queries, which the system matches to stored recipes. Selected recipes are executed in a sandboxed environment, with the system sequentially invoking automated agents according to the DAG structure. The systems and techniques described herein provide real-time feedback during execution and support features such as graphical workflow validation, dynamic parameter collection, role-based access control, and dry run simulations. This approach enables efficient creation and reuse of complex workflows based on natural language inputs.

Abstract: Systems and techniques for large language model based conversational data update are described herein. A natural language input is received that requests a data update via a user interface. The input is evaluated using AI and a large language model to determine update intent. A data update policy is selected and an update command is generated. A virtual data container is created with a subset of data, where the update is executed. The modified data is displayed for user review. Upon confirmation, the update is executed in the main data structure and the virtual container deleted.

Abstract: Systems and techniques for are described herein. Natural language workflow descriptions are received from expert users, the descriptions are processed using language models to identify action sequences, and directed acyclic graphs (DAGs) are generated that represent workflows by mapping actions to automated agents. These DAGs are stored as composite action recipes in a vector database. End users can then submit natural language queries, which the system matches to stored recipes. Selected recipes are executed in a sandboxed environment, with the system sequentially invoking automated agents according to the DAG structure. The systems and techniques described herein provide real-time feedback during execution and support features such as graphical workflow validation, dynamic parameter collection, role-based access control, and dry run simulations. This approach enables efficient creation and reuse of complex workflows based on natural language inputs.

Abstract: Systems and techniques for are described herein. A natural language input is received that requests a data update via a user interface. The input is evaluated using AI and a large language model to determine update intent. A data update policy is selected and an update command is generated. A virtual data container is created with a subset of data, where the update is executed. The modified data is displayed for user review. Upon confirmation, the update is executed in the main data structure and the virtual container deleted.

Abstract: Systems and techniques for a computational unified graph hierarchy model are disclosed herein. A set of source data may be received that may include entity data and relationship data. An entity may be identified in the entity data. A hierarchy may be determined for the entity. An entity graph network may be generated. A non-hierarchical link between the entity and a related entity may be determined. The entity graph network may be updated to include the non-hierarchical link. A set of measures may be generated for a relational link of the entity. A dependency may be configured between the set of measures for the relational link and a second set of measures of a second relational link. A change may be identified to a value of a measure and a dependent entity node measure value may be updated based on a computational effect of the change to the value.

Abstract: A proposed modification to a record of a base data structure is identified, the records of the base data structure sorted by primary key. A type of modification of the proposed modification is identified. A record is added to a differential data structure of the type, the differential data structure record describing the proposed modification. A record is added to a delta data structure sorted by the primary key, the delta data structure record including the primary key value of the record, the type of the proposed modification, and a pointer to the record added to the differential data structure. Data can be fetched using the delta data structure to apply modifications to a set of records requested in the fetch and generate a modified set of records to be returned in a response to the request.

Abstract: A proposed modification to a record of a base data structure is identified, the records of the base data structure sorted by primary key. A type of modification of the proposed modification is identified. A record is added to a differential data structure of the type, the differential data structure record describing the proposed modification. A record is added to a delta data structure sorted by the primary key, the delta data structure record including the primary key value of the record, the type of the proposed modification, and a pointer to the record added to the differential data structure. Data can be fetched using the delta data structure to apply modifications to a set of records requested in the fetch and generate a modified set of records to be returned in a response to the request.

Abstract: Systems and techniques for a computational unified graph hierarchy model are disclosed herein. A set of source data may be received that may include entity data and relationship data. An entity may be identified in the entity data. A hierarchy may be determined for the entity. An entity graph network may be generated. A non-hierarchical link between the entity and a related entity may be determined. The entity graph network may be updated to include the non-hierarchical link. A set of measures may be generated for a relational link of the entity. A dependency may be configured between the set of measures for the relational link and a second set of measures of a second relational link. A change may be identified to a value of a measure and a dependent entity node measure value may be updated based on a computational effect of the change to the value.

Abstract: A proposed modification to a record of a base data structure is identified, the records of the base data structure sorted by primary key. A type of modification of the proposed modification is identified. A record is added to a differential data structure of the type, the differential data structure record describing the proposed modification. A record is added to a delta data structure sorted by the primary key, the delta data structure record including the primary key value of the record, the type of the proposed modification, and a pointer to the record added to the differential data structure. Data can be fetched using the delta data structure to apply modifications to a set of records requested in the fetch and generate a modified set of records to be returned in a response to the request.

Abstract: A change to a particular measure is identified in a particular one of a plurality of business models. A dependency model is identified that identifies relationships between the particular measure and one or more other measures, where the relationships include at least one hierarchical relationship and at least one non-hierarchical relationship. At least a particular one of the one or more other measures are modified based on the change and the relationships.