Complex social problems are at the forefront of our awareness. We are witnessing intensifying political, social and environmental challenges and waning confidence in our ability to engineer solutions. We are also seeing a proliferation of large scale, multi-agency interventions that seek change at the level of systems, and through which actors pursue adaptive learning as a means to develop effective solutions. Proponents assert that the prediction and control on which conventional program design and evaluation are based are not available under complex conditions. They propose instead that learning through experience in a program’s own context can create more responsive, impactful and sustainable interventions. These ideas offer a potentially transformative opportunity. However, they need to be complemented with a better understanding of implementation - the ‘ways of doing things’ that bring them to life. This study focused on developmental evaluation as an example of an adaptive learning (AL) approach for the development of innovative social interventions. The study was informed by ‘sensemaking’ theories and research in organizational learning, knowledge mobilization and program evaluation. Through an exploratory lens and a mixed methods design, this study sheds light on the role of specialized intermediaries in an AL process; how the role is performed in practice; and what this implies for adaptive learning in the domain of social interventions. The study documents how an intermediary can help actors navigate recognized challenges of developing interventions under complex and dynamic conditions. The findings have implications for how an AL process is understood and implemented. They provide an empirical contribution to an emerging field of study on the design of AL systems, to support future research and real-world practice as AL approaches become mainstream.