Deven Varu

Production AI product / Jun 2026 - Present

InterviewWithAI

AI-powered interview practice platform for realistic voice interviews, coding problems, transcripts, and structured performance feedback.

Independent product / Product engineer / Live

Next.js / React / TypeScript / NestJS / Vapi / Monaco Editor / Supabase

InterviewWithAI Project screenshot coming soon

Highlights

  • Built real-time AI interview conversations with Vapi voice agents.
  • Added a browser coding environment with Monaco Editor for technical interview practice.
  • Designed the backend for sessions, questions, transcripts, code submissions, and AI evaluations.

Problem

Interview practice is more useful when speaking, coding, transcripts, and feedback happen in the same workflow instead of separate tools.

What I built

  • A voice interview practice flow using Vapi voice agents.
  • A browser coding environment with Monaco Editor for technical interview practice.
  • Backend models for sessions, questions, transcripts, code submissions, and AI evaluations.

How it works

The product combines a voice-agent interview flow with coding questions and structured feedback so a practice session can include conversation, submitted code, transcript capture, and evaluation data.

Current limitations

Dedicated screenshots and a full public walkthrough still need to be added to the portfolio media library.

View external project Back to projects

Related projects

  • Codex Session Visualizer - VS Code extension that visualizes how Codex explores, reads, edits, creates, and deletes files during AI coding sessions.
  • A2A Multi-Agent Builder - Platform for creating, versioning, and orchestrating multi-agent AI systems dynamically instead of hardcoding workflows.
  • Here2Stay Interest Form - Bilingual web portal for EBPREC that digitized community intake, sent resource packets, and answered housing-resource questions with a RAG chatbot.