Skip to content

Conversation

@samgoodgame
Copy link

Depends on PR #377

Adds a sample demonstrating A2UI for educational applications with custom components (Flashcard, QuizCard), Vertex AI Agent Engine integration, and OpenStax textbook content retrieval.

Includes:

  • Frontend (Vite + Lit)
  • API server (Node.js)
  • Agent (Python ADK)
  • Quickstart notebook and deployment scripts for GCP

This sample showcases A2UI in an educational context - a personalized
MCAT tutor that generates adaptive learning materials (flashcards,
audio, video) based on a learner's profile and identified misconceptions.

Key features:
- A2A agent deployed to Vertex AI Agent Engine generates A2UI content
- Chat orchestrator with Gemini for intent detection
- Demonstrates flashcards, audio player, and video components
- Includes learner context files showing personalization data model
- Educational pages explaining A2UI message flow architecture
…Elements propagation

- Fix bug in surface.ts where enableCustomElements wasn't passed to a2ui-root
- Add Flashcard component with 3D flip animation
- Add QuizCard component with interactive multiple-choice and feedback
- Add theme-provider wrapper for theme context injection
- Add granular OpenStax source attribution for quizzes
- Expand Quickstart.ipynb with detailed NotebookLM audio/video instructions
- Update README with custom component documentation
…from Openstax, and add basic context caching
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant