We discuss the use of the UML to describe “Analysis Patterns” in AI, an area where OAD techniques are not widely used, in spite of the fact that some of the inspiration for the object approach can be traced to developments in this area. We study the relation between the notion of analysis pattern in the context of OO software development methods, and that of Generic Task in AI software development methods such as CommonKADS. Our interest is motivated by the belief that in the analysis and design of certain AI applications, particularly in Distributed AI, OO style patterns may be more appropriate than Generic Tasks. To illustrate the relation between these concepts, we provide a UML description of the heuristic multiattribute decision pattern, a corresponding Generic Task having already been proposed in the literature. We illustrate the wide applicability of this pattern by specialising it to obtain a therapy decision pattern. We discuss the suitability of the UML, together with OCL, for describing this and other analysis patterns arising in AI.