We report results from the first randomization of a regulatory reform in the health sector. The reform established minimum quality standards for patient safety, an issue that has become increasingly salient following the Ebola and COVID-19 epidemics. In our experiment, the census of 1348 health facilities in three Kenyan counties were classified into 273 markets, and the markets were then randomly allocated to treatment and control groups. Government inspectors visited health facilities in treated markets and, depending on the results of their inspection, recommended closure or a timeline for improvements. The intervention increased compliance with patient safety measures in both public and private facilities (more so in the latter) and reallocated patients from private to public facilities without increasing out-of-pocket payments or decreasing facility use. In treated markets, improvements were equally marked throughout the quality distribution, consistent with a simple model of vertical differentiation in oligopolies. Our paper establishes the use of experimental techniques to study regulatory reforms and, in doing so, shows that minimum standards can improve quality across the board without adversely affecting utilization.