@inproceedings{hong_chi2021, author = {Hong, Matthew K. and Fourney, Adam and DeBellis, Derek and Amershi, Saleema}, title = {Planning for Natural Language Failures with the AI Playbook}, year = {2021}, isbn = {9781450380966}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3411764.3445735}, doi = {10.1145/3411764.3445735}, abstract = { Prototyping AI user experiences is challenging due in part to probabilistic AI models making it difficult 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 practitioners from a large technology company revealed that, in addition to challenges prototyping AI, prototyping was often not happening at all or focused only on idealized scenarios due to a lack of tools and tight timelines. These findings informed our design of the AI Playbook, an interactive and low-cost tool we developed to encourage proactive and systematic consideration of AI errors before 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. }, booktitle = {Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems}, articleno = {386}, numpages = {11}, keywords = {AI failures, Human-AI interaction, natural language technologies, prototyping}, location = {Yokohama, Japan}, series = {CHI '21} }