Abstract: A method includes obtaining a request defining a use case. The use case includes a natural language description of a problem. Based on the request, the method includes assigning a plurality of agents to the use case. Each respective agent of the plurality of agents includes a respective trained model. The method includes determining a trigger condition associated with the use case is satisfied. The method also includes, based on determining that the trigger condition is satisfied, executing, by one of the agents of the plurality of agents, a tool associated with the use case.

Abstract: An embodiment may involve persistent storage containing one or more tables, wherein the tables include entries that specify automations, wherein the automations are software applications. One or more processors are configured to: receive a specification for a new automation, wherein the specification includes a frequency at which the new automation is to be executed, and expected time or resources saved per execution; generate an automation request within the tables, wherein the automation request includes the frequency and the expected time or resources saved; generate a reference from the automation request to an automation configuration item (CI) in the tables, wherein the automation CI represents a software application used to perform the new automation; cause the software application to execute at least part of the new automation and in accordance with the frequency; and measure actual time or resources saved per execution of the new automation.

Abstract: An embodiment may involve persistent storage containing one or more tables, wherein the tables include entries that specify automations, wherein the automations are software applications. One or more processors are configured to: receive a specification for a new automation, wherein the specification includes a frequency at which the new automation is to be executed, and expected time or resources saved per execution; generate an automation request within the tables, wherein the automation request includes the frequency and the expected time or resources saved; generate a reference from the automation request to an automation configuration item (CI) in the tables, wherein the automation CI represents a software application used to perform the new automation; cause the software application to execute at least part of the new automation and in accordance with the frequency; and measure actual time or resources saved per execution of the new automation.

Abstract: An embodiment may involve persistent storage containing one or more tables, wherein the tables include entries that specify automations, wherein the automations are software applications. One or more processors are configured to: receive a specification for a new automation, wherein the specification includes a frequency at which the new automation is to be executed, and expected time or resources saved per execution; generate an automation request within the tables, wherein the automation request includes the frequency and the expected time or resources saved; generate a reference from the automation request to an automation configuration item (CI) in the tables, wherein the automation CI represents a software application used to perform the new automation; cause the software application to execute at least part of the new automation and in accordance with the frequency; and measure actual time or resources saved per execution of the new automation.

Abstract: An embodiment may involve persistent storage containing one or more tables, wherein the tables include entries that specify automations, wherein the automations are software applications. One or more processors are configured to: receive a specification for a new automation, wherein the specification includes a frequency at which the new automation is to be executed, and expected time or resources saved per execution; generate an automation request within the tables, wherein the automation request includes the frequency and the expected time or resources saved; generate a reference from the automation request to an automation configuration item (CI) in the tables, wherein the automation CI represents a software application used to perform the new automation; cause the software application to execute at least part of the new automation and in accordance with the frequency; and measure actual time or resources saved per execution of the new automation.

Abstract: An example embodiment involves rules related to repairing software programs, wherein the rules associate indications of software program failures with repair applications that are configured to correct the software program failures. One or more processors are configured to: (i) receive, by a predictive model, a representation of an execution history of a particular software program, wherein the predictive model has been trained on a corpus of execution histories of the software programs; (ii) generate, by the predictive model and from the execution history, a failure prediction for the particular software program; (iii) receive, by an automated repair controller application, the failure prediction from the predictive model; (iv) based on applying the rules to the failure prediction, determine, by the automated repair controller application, a repair application from the repair applications; and (v) cause, by the automated repair controller application, the repair application to be executed within the network.

Abstract: An example embodiment involves persistent storage defining a first configuration item representing an application deployed within a network, a second configuration item representing a software program that is deployable within the network, and a relationship between the first configuration item and the second configuration item. One or more processors may be configured to: (i) receive an indication that a change has been applied to the application or has been arranged to be applied to the application; (ii) identify the relationship between the first configuration item and the second configuration item; (iii) based on the relationship between the first configuration item and the second configuration item, determine that the change can affect operation of the software program; and (iv) in response to determining that the change can affect operation of the software program, provide a notification of the change to an agent associated with the software program.

Abstract: An example embodiment involves persistent storage defining a first configuration item representing an application deployed within a network, a second configuration item representing a software program that is deployable within the network, and a relationship between the first configuration item and the second configuration item. One or more processors may be configured to: (i) receive an indication that a change has been applied to the application or has been arranged to be applied to the application; (ii) identify the relationship between the first configuration item and the second configuration item; (iii) based on the relationship between the first configuration item and the second configuration item, determine that the change can affect operation of the software program; and (iv) in response to determining that the change can affect operation of the software program, provide a notification of the change to an agent associated with the software program.

Abstract: An example embodiment involves rules related to repairing software programs, wherein the rules associate indications of software program failures with repair applications that are configured to correct the software program failures. One or more processors are configured to: (i) receive, by a predictive model, a representation of an execution history of a particular software program, wherein the predictive model has been trained on a corpus of execution histories of the software programs; (ii) generate, by the predictive model and from the execution history, a failure prediction for the particular software program; (iii) receive, by an automated repair controller application, the failure prediction from the predictive model; (iv) based on applying the rules to the failure prediction, determine, by the automated repair controller application, a repair application from the repair applications; and (v) cause, by the automated repair controller application, the repair application to be executed within the network.