We study bank supervision by combining a theoretical model distinguishing supervision from regulation and a novel dataset on work hours of Federal Reserve supervisors. We highlight the trade-offs between the benefits and costs of supervision and use the model to interpret the relation between supervisory efforts and bank characteristics observed in the data. More supervisory resources are spent on larger, more complex, and riskier banks. However, hours increase less than proportionally with bank size, suggesting the presence of technological scale economies in supervision. The data also show reallocation of supervisory hours at times of stress and in the post-2008 enhanced supervisory framework for large banks, providing evidence of constraints on supervisory resources. Finally, we show theoretically limits to assessing supervisory success based on ex-post outcomes, as well as benefits of ex-ante commitment policies.Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.