This talk examines the use of deposition processes involving molecular vapors in precision control of materials for semiconductor applications. Recent work from our group has employed (1) oxidative molecular layer deposition (oMLD) to synthesize sequence-controlled semiconducting polymers as well as (2) functional group lithography to provide patterned deposition on 2D materials. Both these areas provide tremendous opportunities for further development using different molecular vapors, but the vastness of chemical space makes these opportunities daunting. We discuss the use of machine learning tools to reduce the size of chemical space and enable more efficient navigation of chemical space. The future vision for this work includes establishing robust continuously variable parameterization of chemical space, efficient navigation of chemical space through multi-objective Bayesian optimization, and the acceleration of experimental measurements using autonomous labs enabled by robotics and agentic control. These opportunities align with the goals and vision of the MU NRT program on Accelerating Materials Frontiers through Creativity and Data Science, and offer an exciting outlook for the future of experimental materials research at the University of Missouri.