Play 76
Accessibility Learning Agent
High✅ Ready
Screen reader-first, dyslexia-aware learning platform with multi-modal content adaptation.
Inclusive learning platform designed accessibility-first with support for screen readers, dyslexia-friendly rendering, and multi-modal content adaptation. Azure AI Speech provides high-quality text-to-speech and speech-to-text for hands-free learning, OpenAI adapts content complexity and format per learner profile, AI Vision processes visual materials into accessible descriptions, Container Apps hosts the adaptive interface, and Cosmos DB stores personalized accessibility profiles and learning progress.
Architecture Pattern
Accessibility-first: profile detection → content adaptation → multi-modal delivery → progress tracking
Azure Services
Azure AI SpeechAzure OpenAIAzure AI VisionAzure Container AppsAzure Cosmos DB
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — A11y Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (200 lines), evaluate (132 lines), tune (234 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI key input + envFile
TuneKit (AI Config)
- config/openai.json — content simplification and adaptation prompts
- config/accessibility.json — WCAG levels, dyslexia settings, speech profiles
- config/guardrails.json — inclusivity standards, content safety
- evaluation/eval.py — WCAG compliance >AA, User satisfaction >85%
Tuning Parameters
WCAG compliance levelDyslexia font/spacing settingsSpeech rate and voiceContent simplification levelVisual description detail
Estimated Cost
Dev/Test
$80–200/mo
Production
$1.5K–5K/mo