We report on our effort to build a driver support system, Drivers’ Advocate, merging various AI techniques, in particular, agents, ontology, production systems and machine learning technologies. The goal of DA is to help drivers have a safer, more enjoyable and more productive driving experience, by managing their attention and workload. This paper describes the overall architecture of DA, focusing on how agent and machine learning techniques are integrated to make DA intelligently assist drivers. The architecture has been partially implemented in a prototype system built upon a high-fidelity driving simulator to run human experiments. Once DA demonstrates the desired capabilities, it will be tested in a real car in an actual driving environment.