Planning for natural language failures with the ai playbook

Abstract

Prototyping AI user experiences is challenging due in part to proba-bilistic AI models making it difcult to anticipate, test, and mitigate AI failures before deployment. In this work, we set out to support practitioners with early AI prototyping, with a focus on natural language (NL)-based technologies. Our interviews with 12 NL prac-titioners from a large technology company revealed that, in addition to challenges prototyping AI, prototyping was often not happen-ing at all or focused only on idealized scenarios due to a lack of tools and tight timelines. These fndings informed our design of the AI Playbook, an interactive and low-cost tool we developed to encourage proactive and systematic consideration of AI errors be-fore deployment. Our evaluation of the AI Playbook demonstrates its potential to 1) encourage product teams to prioritize both ideal and failure scenarios, 2) standardize the articulation of AI failures from a user experience perspective, and 3) act as a boundary object between user experience designers, data scientists, and engineers.