Sharing my final project: Forsa AI, a voice-first interview practice platform.
What it does: Candidate picks a role (any role, even a custom title) and optionally uploads a CV โ has a real live voice interview with an AI interviewer (GPT-4o via Vapi, WebRTC) โ gets an instant scorecard from Claude, cross-referenced against their CV, plus a downloadable PDF action plan with free courses matched to their weakest areas.
A few engineering decisions I'm happy with:
โข Two-model architecture: GPT-4o live for speed, Claude post-call for structured, schema-guaranteed scoring
โข "Smart Mute" โ muting mid-answer tells the agent to wait, not skip the question
โข A 30-case automated eval suite (npm run eval) that verifies the real prompt/logic wiring, not mocks โ catches real regressions like a dead course link before submission, not after
Thanks to everyone here for the feedback along the way โ happy to answer questions about the Vapi/Claude wiring if anyone's building something similar