I review the data-driven approach to spectroscopy, The Cannon, which is a method for deriving fundamental diagnostics of galaxy formation of precise chemical compositions and stellar ages, across many stellar surveys that are mapping the Milky Way. With The Cannon, the abundances and stellar parameters from the multitude of stellar surveys can be placed directly on the same scale, using stars in common between the surveys. Furthermore, the information that resides in the data can be fully extracted, this has resulted in higher precision stellar parameters and abundances being delivered from spectroscopic data and has opened up new avenues in galactic archeology, for example, in the determination of ages for red giant stars across the Galactic disk. Coupled with Gaia distances, proper motions, and derived orbit families, the stellar age and individual abundance information delivered at the precision obtained with the data-driven approach provides very strong constraints on the evolution of and birthplace of stars in the Milky Way. I will review the role of data-driven spectroscopy as we enter the era where we have both the data and the tools to build the ultimate conglomerate of galactic information as well as highlight further applications of data-driven models in the coming decade.