Objectives: Using agent-based modeling (ABM) within a complexity theory framework provides an alternative and promising method for significantly advancing the study of social good. Complexity theory is a systems approach based on the idea that aggregate patterns arise from the interactions of agents and their environments. Such systems operate according to a set of simple rules, and patterns emerge from these simple interactions that sometimes cannot be predicted by examining those interactions alone. ABM is a computational approach that simulates the interactions of autonomous agents with each other and their environments (social and/or physical). Methods: We adapted the Rebellion model from the NetLogo software library to demonstrate the potential of this approach to measure social good. Specifically, we examine the impact of variables related to juvenile justice involvement on the converse of social good, social exclusion, which in this model was conceptualized as the lack of educational attainment among youth at risk of juvenile justice involvement. After designing our ABM, we ran a total of 2400 simulations where we systematically varied key variables, including arrest risk and maximum sentence. Results: We report the descriptive statistics from our simulations for key output variables in the ABM, including percent socially excluded and average accumulated jail time, and demonstrate the usefulness of this method by identifying nonlinear, bivariate associations across the simulations. Conclusion: Our model demonstrates the usefulness of an innovative methodological approach, complexity theory, coupled with an innovative technology, ABM, in developing policies and programs that will maximize social good.