Designing artificial intelligence applications in law: A systemic view

Artificial intelligence applications development in law has historically focused on formal legal reasoning. Most of the systems are rule-based and none has yet become a fully functional prototype or commercially viable. The attempts to build large-scale systems without examining the intrinsic systemic nature of the legal process has resulted in limited operational success. The legal function, another area of legal activity, has emerged rapidly offering potential for artificial intelligence-based applications. This paper discusses the systemic differences between legal reasoning and legal function and suggests that different design methodologies be used in the two domains. Legal reasoning requires a holistic approach such as the blackboard model incorporating the properties of softness, openness, complexity, flexibility, and generality of legal systems, while traditional rule-based approaches are sufficient for legal function applications.