SHRAVYA AI-Powered live Interview Panel
Link to open source: https://github.com/shravanivarale/Echo-Sphere
Link to Live Project: https://echo-sphere-black.vercel.app/
Shravya — Three AI Experts. One Intelligent Interview.
Shravya is a voice-native, multi-agent AI interview platform built around Agora’s real-time communication infrastructure. It brings together three specialist AI interviewers—a System Architect, a Product Manager, and a Security Lead—to evaluate candidates through a shared, adaptive conversation. Each agent contributes a distinct perspective, while an orchestration layer manages context and speaking turns.
Its defining innovation is intra-panel friction: agents can challenge one another’s priorities and ask candidates to resolve real-world trade-offs. When a candidate proposes a complex architecture, the System Architect examines scalability, the Product Manager questions delivery timelines, and the Security Lead investigates vulnerabilities. This creates opportunities to assess technical depth, practical judgment, and decision-making.
Through live voice-to-workspace synchronization, the panel also follows code and architecture diagrams as candidates work. Changes in the shared workspace inform follow-up questions, connecting what candidates explain with what they actually build. Interruption handling is designed to keep the conversation natural and responsive.
After the interview, assessment engine links competency scores and feedback to timestamped transcript and audio evidence. Recruiters can review the reasoning behind each assessment and retain responsibility for the final hiring decision.
Shravya aims to make expert interviews available on demand, reveal how candidates reason, and give hiring teams evidence they can inspect.
This build was uploaded as a hackathon project
