In recent years, Artificial Intelligence has become more and more relevant in our society. Creating AI systems is almost always the prerogative of IT and AI experts. However, users may need to create intelligent solutions tailored to their specific needs. In this way, AI systems can be enhanced if new approaches are devised to allow non-technical users to be directly involved in the definition and personalization of AI technologies. End-User Development (EUD) can provide a solution to these problems, allowing people to create, customize, or adapt AI-based systems to their own needs. This paper presents a systematic literature review that aims to shed the light on the current landscape of EUD for AI systems, i.e., how users, even without skills in AI and/or programming, can customize the AI behavior to their needs. This study also discusses the current challenges of EUD for AI, the potential benefits, and the future implications of integrating EUD into the overall AI development process.

翻译：近年来，人工智能在社会中的相关性日益增强。创建AI系统几乎始终是IT和AI专家的专属领域。然而，用户可能需要定制符合其特定需求的智能解决方案。因此，若设计出新方法使非技术用户能够直接参与AI技术的定义与个性化，AI系统将得以增强。最终用户开发（End-User Development, EUD）可为这些问题提供解决方案，使用户能够根据自身需求创建、定制或适配基于AI的系统。本文通过系统文献综述，旨在阐明当前面向AI系统的EUD领域现状，即用户如何在缺乏AI和/或编程技能的情况下，根据自身需求定制AI行为。本研究同时讨论了面向AI的EUD当前面临的挑战、潜在优势，以及将EUD整合至整体AI开发流程中的未来启示。