As artificial intelligence (AI) models and services are used in a growing number of high-stakes areas, a consensus is forming around the need for a clearer record of how these models and services are developed to increase trust. Several proposals for higher quality and more consistent AI documentation have emerged to address ethical and legal concerns and general social impacts of such systems. However, there is little published work on how to create this documentation. In this paper we describe a methodology for creating the form of AI documentation we call FactSheets. This paper describes the methodology and shares the insights we have gathered while creating nearly two dozen FactSheets. Within each step of the methodology, we describe the issues to consider and the questions to explore with the relevant people in an organization who will be creating and consuming AI facts. This methodology may help foster the creation of transparent AI documentation.