If education policy-making is based strictly on rigorous evidence there is a risk of bias towards simple, discrete, measurable interventions. We present a framework for considering inconclusive evidence. If education policy-making is based strictly on rigorous evidence there is a risk of bias towards simple, discrete, measurable interventions. We present a framework for considering inconclusive evidence – through systematic consideration of the estimated costs, benefits and potential harm of a policy, along with the uncertainty in those estimates. This allows for a rational approach to pursuing or testing policies lacking rigorous evidence. The framework also suggests research methodologies to improve the rigour of evidence for interventions that are complex or highly context-dependent. The aim is to make evidence-based decision making more widely applicable and more effective. Matthew Jukes has two decades of academic and professional experience in evaluating international education projects, particularly in early-grade literacy interventions and the promotion of learning through better health. Dr Jukes’ current research addresses culturally relevant approaches to assessment of social and emotional competencies in Tanzania; improving pedagogy through an understanding of the cultural basis of teacher-child interactions; frameworks to improve evidence-based decision-making; and methods to set reading proficiency benchmarks. Previous roles include Senior Director of Global Research, Monitoring and Evaluation at Room to Read and Associate Professor of International Education at the Harvard Graduate School of Education.