While there’s much excitement about machine learning (ML), the ML models driving our daily interactions are often blackboxed and inaccessible to the broader audience. A major problem is the lack of concrete visual representations that any user can manipulate to understand their results. We aim to provide an accessible ML representation by coupling the data and model with a visual-rule based interface. We present Learner’s Permit, an interactive programming game where the player’s objective is to teach a car to drive itself. In Learner’s Permit, we aim to support the entire ML workflow, including data collection, training, testing and debugging. By combining the principles of visual rule programming and interpretable AI, we are able to build a novel game that makes ML accessible for all audiences.