Ultravox speech-to-speech, Twilio Voice, and a LangGraph dialogue policy that branches on each candidate response. ATS-native scoring across Greenhouse, Lever, Workday, Ashby, and 4 more.
We've worked with high-volume retail recruiters, BPO talent ops, and tech-screening teams. The breakdowns are the same.
Recruiters take 15-25 minutes per phone screen and triage 40-60 applicants per role
Each recruiter improvises questions, applies different rubrics, and writes free-form notes
Roles in retail, BPO, and hospitality see candidates across 5-10 languages with no bench depth
Pre-recorded one-way video assessments see 45-60% candidate abandonment
Retail, customer support, and seasonal hiring need thousands of screens per month
Recruiters take 15-25 minutes per phone screen and triage 40-60 applicants per role
Top candidates accept other offers before reaching the hiring manager
$8K-15K per role lost to slow time-to-shortlist
Bottom Line: Manual phone screening doesn't scale with applicant volume, and async video screening trades scale for candidate experience.
Six named components, each picked for a specific failure mode of the typical voice-AI stack.
Sub-300ms turn-taking on real phone audio. No transcription hop in the critical path, so the conversation actually feels human.
Outbound and inbound calls with carrier-grade quality, MOS telemetry per call, and automatic fallback when packet loss spikes.
Dialogue is a state machine, not a fixed script. Senior engineers get deeper system-design probes; entry-level candidates stay on shorter branches.
Every scored criterion cites the exact candidate utterance that supports it. The PDF report is defensible against scorecard disputes and audit requests.
Speech-to-speech in 22 languages including Spanish, Mandarin, Arabic, Hindi, Urdu, Tagalog, Portuguese, German, French, Japanese. Code-switching tracked mid-call.
Scorecards, transcripts, and PDF reports push directly into Greenhouse, Lever, Workday Recruiting, BambooHR, iCIMS, JazzHR, Ashby, and SmartRecruiters.
From recruiter rubric to compliance-ready PDF — the actual flow, not a marketing diagram.
Recruiter posts the role and a weighted scoring rubric with expected evidence patterns per criterion. Templates exist for common role families.
OpenAI-powered scheduling agent reads candidate availability via Google Calendar or Outlook and books the slot without recruiter touch.
Outbound dial with carrier-grade quality. MOS, jitter, and packet loss monitored per call; degraded calls trigger callback or channel switch.
Unified speech-to-speech runs the conversation with sub-300ms turn latency. Whisper available as fallback STT; ElevenLabs for premium brand TTS personas.
Each response routes through an evaluator node. Strong answers branch deeper; weak signals trigger probing follow-ups; off-topic answers re-anchor to the rubric.
Anthropic Claude scores against the rubric live, with every score tied to a cited candidate utterance. No post-hoc transcription review.
PDF report with evidence citations writes to the ATS. Slack notifies the recruiter when a candidate clears threshold. Sentry tracks production errors end-to-end.
Greenhouse, Lever, Workday Recruiting, BambooHR, iCIMS, JazzHR, Ashby, SmartRecruiters, Google Calendar, Outlook Calendar, Slack for recruiter notifications. Sentry for production error tracking across the Ultravox, Twilio, and LangGraph layers.
Not every role needs voice AI. These four pipelines are where the math works.
Retail, hospitality, BPO, and customer support pipelines screening thousands of applicants per month per region.
Multilingual screens in 8-12 languages, availability and reliability scoring, automated reschedule flows for no-shows.
Competency-based screens for senior backend, ML, and platform engineers before they hit the hiring manager loop.
System design probes, language and framework depth checks, behavioral evidence on prior shipped systems.
Consulting, accounting, and legal-ops associate pipelines where structured behavioral scoring drives the decision.
Case-style follow-ups, client-facing communication scoring, structured evidence for partner review.
University recruiting, apprenticeships, and early-career programs with thousands of applicants per cohort.
Lower-anxiety conversational format outperforms async video on completion and candidate NPS by 30+ points.
Numbers from the production pipeline, not pilot demos.
Cognilium handles dialogue engineering, ATS integration, and production monitoring. You bring the rubric and the candidates.
We capture your scoring criteria, evidence patterns, calibration examples, and ATS configuration. Recruiter interviews to surface implicit rubric.
50-100 real candidate screens with side-by-side recruiter shadow scoring. Calibration report against rubric drift and adverse-impact baseline.
Multi-ATS integration, multilingual rubric pass with native-speaker calibration, Slack and calendar wiring, Sentry production monitoring.
Monthly adverse-impact audit, rubric drift detection, latency and MOS regression monitoring, and quarterly model upgrades.
Latency, integration, bias, compliance, fallback behavior — all of it.