The vision of fully automated manufacturing processes was conceived when computers were first used to control industrial equipment. But realizing this goal has not been easy; the difficulties of generating manufacturing information directly from computer aided design (CAD) data continued to challenge researchers for over 25 years. Although the extraction of coordinate geometry has always been straightforward, identifying the semantic structures (i.e., features) needed for reasoning about a component’s function and manufacturability has proved much more difficult. Consequently the programming of computer controlled manufacturing processes such as milling, cutting, turning and even the various lamination systems (e.g., SLA, SLS) has remained largely computer aided rather than entirely automated. This paper summarizes generic difficulties inherent in the development of feature based CAD/CAM (computer aided manufacturing) interfaces and presents two alternative perspectives on developments in manufacturing integration research that have occurred over the last 25 years. The first perspective presents developments in terms of technology drivers including progress in computational algorithms, enhanced design environments and faster computers. The second perspective describes challenges that arise in specific manufacturing applications including multiaxis machining, laminates, and sheet metal parts. The paper concludes by identifying possible directions for future research in this area.