Mathematical models drawn from several modeling traditions play an important role in decision support. This paper describes PDM, a knowledge-based tool designed to help non-expert users construct Linear Programming (LP) models of Production, Distribution and Inventory (PDI) planning problems. PDM interactively aids users In defining a logic model of their planning problem and employs it to generate problem-specific inferences and as input to a model building component that mechanically constructs the algebraic schema of the appropriate LP model. Interesting features of PDM include the application of domain knowledge to guide user interaction, the use of syntactic knowledge of the problem representation language to effect model revision, and in the use of a small set of primitive modeling rules in model construction.