Tyvur AI

Overview

Tyvur is an AI-powered platform for practicing realistic technical interviews. I built and deployed it end to end: the AI layer, real-time voice flow, backend, frontend, auth, subscriptions, and payments. It creates an AI interviewer that understands a candidate's resume and target role, conducts personalized interviews, evaluates answers, and generates detailed feedback.

Product Demo

The Problem

Most interview prep tools are static question banks or text chatbots. Neither simulates the pressure of speaking out loud in a real interview. Tyvur was built so candidates can practice conversations that feel real and get specific feedback on where their answers were weak.

What It Does

• • Personalized mock interviews based on resume and target role
• • Voice-based practice that simulates real interview pressure
• • Contextual follow-up questions that probe weak or vague answers
• • Answer-level feedback with specific improvement suggestions
• • Role-based interview modes aligned to what the candidate is preparing for

What I Built

• • AI orchestration for multi-step, stateful interview flows
• • State management so sessions survive disconnects and restarts
• • Real-time communication for turn-based voice interviews
• • Voice processing with speech-to-text in a conversational loop
• • Backend and data layer for users, sessions, resumes, and history
• • SaaS infrastructure including auth, subscriptions, and payment webhooks
• • Production deployment as a live product handling real users

Challenges

• • Personalized interviews from unstructured resumes in PDF and DOCX formats
• • Voice interviews that feel conversational, not like a rigid Q&A script
• • Long-running sessions that stay coherent across many turns
• • Reliability when external AI services timeout or fail mid-interview
• • End-to-end ownership across frontend, backend, AI, and infrastructure

Further Reading