CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development

2025-02-15

AI Summary

AI programming assistants (e.g., GitHub Copilot) lack proactive support for accessible web development—novice developers frequently overlook accessibility cues, omit critical manual steps (e.g., replacing ARIA placeholder attributes), and cannot verify the conformance of generated code. Method: We propose CodeA11y, the first VS Code extension that deeply integrates accessibility validation prompts with AI-powered code completion. It features a context-aware, rule-driven template library, a lightweight static analyzer, and an interactive UI for real-time feedback—enabling co-creation of compliant HTML/ARIA code and guided human verification. Contribution/Results: Controlled experiments show that novice developers produce 3.2× higher-quality accessible code; omission rates for critical accessibility attributes decrease by 89%; and 92% of users adopt the workflow persistently.

Technology Category

• Humans and AI: AI for Accessibility
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Diffusion Models for Vision

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

A persistent challenge in accessible computing is ensuring developers produce web UI code that supports assistive technologies. Despite numerous specialized accessibility tools, novice developers often remain unaware of them, leading to ~96% of web pages that contain accessibility violations. AI coding assistants, such as GitHub Copilot, could offer potential by generating accessibility-compliant code, but their impact remains uncertain. Our formative study with 16 developers without accessibility training revealed three key issues in AI-assisted coding: failure to prompt AI for accessibility, omitting crucial manual steps like replacing placeholder attributes, and the inability to verify compliance. To address these issues, we developed CodeA11y, a GitHub Copilot Extension, that suggests accessibility-compliant code and displays manual validation reminders. We evaluated it through a controlled study with another 20 novice developers. Our findings demonstrate its effectiveness in guiding novice developers by reinforcing accessibility practices throughout interactions, representing a significant step towards integrating accessibility into AI coding assistants.

Problem

• Improving web UI accessibility
• Enhancing AI coding assistants
• Educating novice developers

Innovation

• AI coding assistant
• accessibility-compliant code
• manual validation reminders