CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development

Peya Mowar1 Yi-Hao Peng1 Jason Wu2 Aaron Steinfeld1 Jeffrey Bigham1,2

1Carnegie Mellon University    2Apple

ACM CHI 2025

VS Code CodeA11y

ACM DL ACM / PDF Paper / GitHub Code / YouTube Video / PPT Slides

The interface of the extension is displayed along with its features: (1) Accessibility-by-default Code Suggestions, (2) Relevant Error Identification and (3) Code Completion Reminders.

CodeA11y is a GitHub Copilot Extension for Accessible Web Development. CodeA11y addresses accessibility limitations of Copilot observed in our study with developers through three features: (1) accessibility-by-default code suggestions, (2) automatic identification of relevant accessibility errors, and (3) reminders to replace placeholders in generated code. Integrating these features directly into AI coding assistants would improve the accessibility of the user interfaces (UIs) developers create.

@inproceedings{10.1145/3706598.3713335,
author = {Mowar, Peya and Peng, Yi-Hao and Wu, Jason and Steinfeld, Aaron and Bigham, Jeffrey P},
title = {CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development},
year = {2025},
isbn = {9798400713941},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3706598.3713335},
doi = {10.1145/3706598.3713335},
booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
articleno = {45},
numpages = {15},
keywords = {AI Coding Assistants, Web Accessibility, Coding Agents, AI Agents},
location = {Yokohama, Japan},
series = {CHI '25}
}