Enterprise API design is often bottlenecked by the tension between rapid feature delivery and the rigorous maintenance of usability standards. We present an industrial case study evaluating an AI-assisted design workflow trained on API Improvement Proposals (AIPs). Through a controlled study with 16 industry experts, we compared AI-generated API specifications against human-authored ones. While quantitative results indicated AI superiority in 10 of 11 usability dimensions and an 87% reduction in authoring time, qualitative analysis revealed a paradox: experts frequently misidentified AI work as human (19% accuracy) yet described the designs as unsettlingly "perfect." We characterize this as a "Perfection Paradox" -- where hyper-consistency signals a lack of pragmatic human judgment. We discuss the implications of this perfection paradox, proposing a shift in the human designer's role from the "drafter" of specifications to the "curator" of AI-generated patterns.
@article{arxiv.2603.12475,
title = {The Perfection Paradox: From Architect to Curator in AI-Assisted API Design},
author = {Mak Ahmad and Andrew Macvean and JJ Geewax and David Karger},
journal= {arXiv preprint arXiv:2603.12475},
year = {2026}
}
Comments
6 pages, 2 figures, 3 tables; Poster paper at CHI EA 2026 (Extended Abstracts of the ACM CHI Conference on Human Factors in Computing Systems)