Abstract: A method for evaluating a build of a computer-implemented game is disclosed. An evaluation request is received. The evaluation. request includes an identification of the build, data describing one or more behaviors for the build, and data describing one or more tests. One or more simulations of playing of the build are performed using the one or more behaviors. One or more metrics ate extracted from the simulations. Each of the one or more metrics measures an aspect of the computer-implemented game. One or more tests are applied to the one or more metrics to evaluate an adherence of the build to the one or more tests. A display of the evaluation is caused to be displayed in a user interface of a client device.