Verified neural Lyapunov function for a two-machine power system. Credit: Automatica (2025). DOI: 10.1016/j.automatica.2025.112193 As artificial intelligence (AI) takes on increasingly critical roles—from managing power grids to piloting autonomous vehicles—making sure these systems are safe has never been more important. But how can we be certain that the AI controlling them can be trusted? A research team at the University of Waterloo is addressing this