The astronomers’ goal: find an artificial intelligence algorithm to interpret microlensing events captured by the upcoming Roman Space Telescope and speed detection of exoplanets around other stars. They achieved that, but the AI told them something unexpected and deep: the theory used to infer stellar and exoplanetary masses and orbits from observations was incomplete. Digging into the mathematics, they uncovered a theory that explains all types of microlensing events and possible ambiguities in interpreting them.