Advances in impact modelling and numerical weather forecasting have allowed accurate drought monitoring and skillful forecasts that can drive decisions at the regional scale. State-of-the-art drought early warning systems are currently based on statistical drought indicators, which do not account for regional vulnerabilities, and hence neglect the socio-economic impact for initiating actions. The transition from conventional physical forecasts of droughts towards impact-based forecasting (IbF) is a recent paradigm shift in early warning services, to ultimately bridge the gap between science and action. The demand to generate predictions of “what the weather will do” underpins the rising interest in drought IbF across all weather-sensitive sectors. Despite the socio-economic benefits are expected to be high, migrating to this new paradigm presents myriad challenges. In this paper, we outline the progress in IbF of drought, and present a road map highlighting current challenges and corresponding needs for advancing this emerging field. More specifically, we identify the main disconnects and biases of the science and practice of IbF of drought, namely contextual bias (inadequate accounting for the spatio-sectoral dynamics of vulnerability and exposure), data bias (mainly textual and lacking collection protocols for all sectors), model bias (mostly reliant on machine learning models), sectoral bias (mainly agriculture in the science), and geography (mainly Europe for the science, and developing regions in the practice). Our vision is to facilitate the IbF progress and its use in making informed and timely decisions on mitigation measures, thus minimizing the impacts of droughts globally.