Project Overview

Ava is a conversational AI healthcare assistant integrated into iMessage that helps University of Washington students navigate healthcare services by translating symptoms into structured clinical signals and routing them to the appropriate care destination.

Team Members: Alley Wu, Ani Ramadurai, Katharina Cheng, Mekias Kebede, Sofila Song

Process

Research: Interviewed UW students, validated that 94% use iMessage daily and most are unfamiliar with healthcare. Created persona "Alex Chen" - international student unfamiliar with U.S. healthcare.

Design: Built symptom understanding system, care routing logic, and plain-language feedback. User testing revealed responses were too long - pivoted to add interactive elements (buttons/options) and requested features (cost estimation, in-network providers).

Development: Implemented pre-classification system, multi-language translation, and care routing with next steps.

Team Actions

• Collectively chose iMessage platform based on usage data

• Established ethical boundaries: "triage support" not "diagnosis"

• Iteratively tested and refined based on user feedback

• Developed privacy-first approach with minimal data collection

Key Takeaways

• User needs evolve: Started with triage, pivoted to full care navigation

• Ethics require proactive design: Clear language about AI limitations builds trust

• Platform matters: Familiar interfaces (iMessage) reduce adoption friction

• Iteration is essential: User testing drove major improvements in UX

  
  

Outcomes & Final Deliverables

Completed Improvements:

• Enhanced onboarding process with interactive responses

• Refined user flow based on testing feedback

• Implemented core symptom translation and care routing system

Project Conclusion:

The Ava project successfully demonstrated a privacy-first approach to healthcare navigation for students. While the project concluded at the end of Spring Quarter 2026, it validated key insights about accessible healthcare technology and the importance of platform-native design.

Potential Future Directions (if development were to continue):

• Insurance-based recommendations and cost estimation features

• Clinic visit script generation

• Conversation encryption for enhanced privacy

• Expansion to other university health systems

• Integration with health consulting services and impact tracking

Links: Demo Video | Code Repo