Back to selected work

Gemini Live Agent Hackathon · 2026

Cognito

A real-time, voice-and-vision AI tutor that scores and surfaces a student's 'flow state' live during a session.

What was hard

A real-time tutor is only useful when its voice and vision session survives the messy parts of a live connection.

What I built

A Gemini Live API tutor on FastAPI and Cloud Run, with WebSocket streaming, structured error envelopes, and a dismissible recovery banner.

What I learned

Realtime reliability is state management: reconnects, audio ownership, and session hydration are product behavior, not edge cases.