Not a feature list — the actual mechanisms underneath the voice interviewer: a fused turn-taking model that proves it's safe before it interrupts you, a memory engine written in Rust from scratch, and a report generator that deletes its own claims rather than invent a citation. Every number below is either a gate enforced in CI or labelled as a target.
Most voice agents guess when you're done talking from silence alone. Ours fuses 13 signals every 50ms — VAD, prosody, partial-ASR stability, and semantic completeness — into an endpoint predictor that outputs three separate calibrated probabilities, each Platt-scaled against labelled data:
At boot, the system replays a labelled mock-interview corpus through the endpoint predictor and measures how often it would have falsely interrupted a candidate who was still thinking. That rate has to clear a gate before backchannels are allowed to speak at all:
Measured on labelled HOLD points from the mock corpus. Above the gate, or if the corpus is missing, or if the eval itself errors — the mode pins to shadow, not live.
Every backchannel and co-completion decision is logged and scored against ground truth in production, silently, until the measured rate earns the right to go live.
The five-tier silence ladder runs on pause-tolerance tiers multiplied by a single documented constant, so the calibration is something an auditor can actually point at:
Co-completion is only allowed to close safe grammatical tails — and is hard-blocked by regex from ever completing anything that matches a number, an architecture term, or a scored claim. Two wrong completions in a single session disable it entirely, for that candidate, for the rest of the interview.
Not a wrapped vector database — a purpose-built quantization scheme (“TurboQuant”): a seeded orthogonal rotation, a Lloyd-Max 3-bit codebook, a 1536-bit QJL residual sketch, and a two-stage scan that reranks the sketch's shortlist against full fp16 vectors. Served over gRPC, contract frozen and additive-only since 2026-05-21.
Every turn is traced through audio capture, ASR finalization, endpoint commit, answer embedding, memory recall, context assembly, the next-question model, and first-audio TTS — each stage flagged the instant it goes over budget, with live p95 queryable in production.
The report drafts in one JSON-mode call, deliberately separate from the latency-tuned interview brain. Then every cited turn is re-resolved against the actual transcript: a citation to a turn that doesn't exist is dropped, and a claim left with zero valid citations is deleted from the report entirely — not flagged, removed.
This is the part most pitches skip.
No pricing here, no pilot to book — just the mechanisms. If you're evaluating the engineering directly, the build log is in the journal, and a real inbox is on the other end of the email below.