A natural language interface is proposed as a part of the solution to the problem posed by the continuing increase in the number and sophistication of CAD tools. The advantages of a natural language interface for CAD are numerous, but the complexity of the CAD domain renders most previous work in natural language interfaces of limited utility. A new approach to natural language understanding is described which is being implemented in an interface currently under development. This approach is based on flexibility, parallelism, and redundancy. The present status of the interface (named Cleopatra) is described, and some improvements are discussed.