Grid computing provides key infrastructure for distributed problem solving in dynamic virtual organizations. It has been adopted by many scientific projects, and industrial interest is rising rapidly. However, Grids are still the domain of a few highly trained programmers with expertise in networking, high-performance computing, and operating systems. This paper describes our initial work in capturing knowledge and heuristics about how to select application components and computing resources, and using that knowledge to generate automatically executable job workflows for the Grid. Our system is implemented and integrated with a Grid environment where it has generated dozens of workflows with hundreds of jobs in real time. The paper also discusses the prospects of using AI to improve current Grid infrastructure.