We study the optimal intervention policy to stop projects in a relational contract between a principal and a policymaker. The policymaker is privately informed about his ability and privately chooses how much effort to exert. Before a project is completed, the principal receives a signal about its outcome and can intervene to stop it. Intervention may prevent a bad outcome, but no intervention leads to better learning about the policymaker’s ability. In the benchmarks with observable effort or observable ability, optimal intervention follows a threshold rule. With unobservable effort and ability, the optimal policy switches between intervention and no intervention.