Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing an experiment for a workforce analytics system. One of the methods includes identifying team members who conduct work using a heterogeneous set of software tools including third party software tools. An experiment group of team members and a control group of team members are identified. Experiment activity data is received from use by the experiment group of the set of heterogeneous software tools and control group activity data is received from use by the control group of the set of heterogeneous software tools. A metric by which to measure the effect of a process change is identified. The effect of the process change is determined according to the metric and based on the experiment activity data and the control group activity data. Action is taken based on the effect of the process change.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining true utilization based on productive behaviors of operators in a digital environment. One of the methods includes automatically determining productivity for each of multiple users of an organization. Timing data for a user is received that indicates available work time for the user. Interaction data is received for the user for interactions by the user during the available work time for the user. Productivity rules for an organization of the user are received that define productivity of interactions by users of the organization. Productivity of interactions of the user is determined based on the interaction data and the productivity rules. True utilization for the user is determined based on the productivity of the interactions and the timing data. Action data is generated based on the determined true utilization action is taken based on the action data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automating actions based on ranked work events. A sequence of events are tracked which occur in software services accessed by a user, tracking events from each case handled by the user. Focus events are determined which identify which case is being worked on by the user at points in time. The determination is made using information extracted from user interactions with at least one service, where each focus event has a focus event duration. Each focus event is assigned to a particular case. A total period of time spent by the user on the particular case is determined. Work actions of the users are ranked. The ranking includes receiving an indication of reviewer intent for ranking the work actions, generating a set of work actions, and prioritizing the set of work actions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automatic generative learned process coaching. One of the methods includes receiving interaction data for a user for interactions occurring in multiple software services used by the user during handling of a case. A case type of the case is determined and a machine learning model that includes learned model interaction behavior for the case type is identified. Interaction data for the user is compared to the learned model interaction behavior for the case type. Action data is generated for the user that includes an interaction behavior improvement recommendation that is determined based on the comparing of the interaction data for the user to the learned model interaction behavior for the case type. Action is taken based on the action data.