Peya Mowar
banner
peyajm29.bsky.social
Peya Mowar
@peyajm29.bsky.social
grad @scsatcmu.bsky.social | prev @msftresearch.bsky.social | #ai, #hci, #a11y
cs.cmu.edu/~peyajm29
Reposted by Peya Mowar
the tool does three main things --
1) accessible by default code suggestions
2) built-in accessibility error detection, and
3) reminders to complete template code
April 30, 2025 at 12:24 AM
Reposted by Peya Mowar
using CodeA11y, people created more accessible code --
April 30, 2025 at 12:25 AM
Thanks Mina!! :)
March 26, 2025 at 4:50 AM
Thank you! :)
March 25, 2025 at 9:13 PM
Thanks Frank! :)
March 25, 2025 at 3:02 PM
Thank you so much :)
March 25, 2025 at 3:02 PM
Big thanks to my collaborators: @jeffreybigham.com @yihaopeng.bsky.social, Jason Wu and Aaron Steinfeld
February 18, 2025 at 5:19 PM
A technical evaluation of CodeA11y with 20 developers demonstrated a statistically significant improvement in producing accessible UI code without compromising their satisfaction and ease of use.
(5/n)
February 18, 2025 at 5:19 PM
We built CodeA11y, a GitHub Copilot Extension that addresses the observed gaps by consistently reinforcing accessible development practices throughout the conversational interaction.
(4/n)
February 18, 2025 at 5:19 PM
Our formative study with 16 developers revealed 3 barriers to this opportunity: i) developers failed to prompt for accessibility considerations explicitly, ii) uncritically accepted incomplete suggestions, and iii) struggled to detect accessibility issues in their code.
(3/n)
February 18, 2025 at 5:19 PM
Prior work shows getting front-end developers to write accessible UI code has proven exceptionally difficult. We argue that AI coding assistants (e.g., Github Copilot), already widely adopted, could offer an opportunity to make UI code more accessible.
(2/n)
February 18, 2025 at 5:19 PM
Thank you! :)
November 20, 2024 at 8:36 PM