To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some understanding of AI operations can support predictability, but forcing AI to explain itself risks constraining AI capabilities to only those reconcilable with human cognition. We argue that AI systems should be designed with features that build trust by bringing decision-analytic perspectives and formal tools into AI. Instead of trying to achieve explainable AI, we should develop interpretable and actionable AI. Actionable and Interpretable AI (AI 2 ) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. In doing so, it will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making and ensure broad benefits from deploying and advancing its computational capabilities.
Decision Making: Humans and Artificial Intelligence (AI)"Can I trust the recommendation of an AI agent?" This question is difficult to answer, especially if the decision at stake is complex and spans different spatial and temporal scales. Such difficulty is exacerbated when the outcomes of an AI-influenced decision may heighten existing risks to humans or introduce new risks altogether. Yet such high-stakes situations have become routine within the diverse systems that currently incorporate AI, like controls for chemical plants, defense systems, and health insurance rate determinations. Stakeholders must be prepared not only to configure AI and its enabling technologies for a given industry or activity, but also to have tools and methodologies to examine and recognize its failures, limitations, and needs for quality control at various stages of its development and implementation.The ultimate goal of AI is to provide users with actionable recommendations that meet both implicit and explicit goals of the decision makers and stakeholders. Recommendations generated from AI-based