On average, an approved drug currently costs US$2–3 billion and takes more than 10 years to develop. In part, this is due to expensive and time-consuming wet-laboratory experiments, poor initial hit compounds and the high attrition rates in the (pre-)clinical phases. These challenges also affect small-molecule drug development projects aiming to reverse addiction and prevent drug abuse. Structure-based virtual screenings have the potential to mitigate the above mentioned problems. Within structure-based virtual screenings, the quality of the hits improves with the number of compounds screened. In this talk I will describe VirtualFlow, a highly automated and versatile drug discovery platform with perfect scaling behaviour that is able to prepare and efficiently screen ultra-large libraries of compounds. VirtualFlow was the first platform able to routinely screen billions of commercially available molecules.