The Generable platform is utilizing the latest advances in probabilistic programming, Bayesian inference, and multi-level regression and poststratification (MRP) for dose optimization, making go/no-go decisions from early clinical data, assessing the predictive power of biomarkers, and performing principled subgroup analysis. Our cloud-based, analytics-ready database and inference API makes it easy to produce and reproduce analyses without worrying about IT infrastructure configuration and maintenance. We are currently working with a small number of beta customers in Immuno-Oncology. Generable originated from the open-source Stan (mc-stan.org) project at Columbia University.