This article comments on the role of empirical subjective well-being research in public policy within a constitutional, procedural perspective of government and state. It rejects the idea that, based on the promises of the measurement, we should adopt a new policy perspective that is oriented towards a decision rule maximizing some aggregate measure of subjective well-being. This social engineering perspective, implicit in much reasoning about well-being policy, neglects i) important motivation problems on the part of government actors, such as incentives to manipulate indicators, but also on the part of citizens to truthfully report their well-being, and ii) procedural utility as a source of well-being. Instead, well-being research should be oriented towards gaining insights that improve the diagnoses of societal problems and help to evaluate alternative institutional arrangements to address them, both as inputs into the democratic process.