AI Agents
Discovery Express

People & talent

Voice Interviewer

Screens every candidate by phone the same day they apply, with a structured scorecard in your ATS.

In productionReviewed September 3, 2026
Packaged as Reclutalia
Voice · Voice Interviewer
Demo data

  1. Candidate

    Yes, I have two years driving a forklift, most of it on the night shift.

  2. Agent

    Thanks. Which certification do you hold, and when does it expire?

  3. Workable · scorecard written · must-haves 5/5 · experience 4/5 · recording attached

  4. Handoff to a person

    Borderline on availability: sent to the recruiter with the recording. No rejection is sent automatically.

VoiceReclutaliaWorkableOther ATS
KPI it moves
1,000 calls per month to 1,000 per hourMeasured
Channels
VoiceWhatsApp
Integrates
  • Reclutalia
  • Workable
  • Other ATS
  • Google Calendar / Outlook
  • Telephony
A recruiter reviewing interview notes beside a stack of resumes in a Monterrey office
People & talent

What it does

Every candidate called the day they apply. Every call scored the same way.

Where it lives

Your cloud, your repo, your IP.

1. Receives 2. Looks up 3. Decides 4. Acts 5. Escalates 6. Learns

Channels

  • Voice
  • WhatsApp

Voice Interviewer

03Decides

Systems it integrates

  • Reclutalia
  • Workable
  • Other ATS
  • Google Calendar / Outlook
  • Telephony

A person on your team

01

Receives

Takes the application from the ATS or a WhatsApp reply and schedules or starts the call at once.

02

Looks up

Loads the role's interview guide, the must-have requirements and the recruiter's scoring rubric.

03

Decides

Chooses the follow-up questions from the candidate's answers, in Spanish or English.

04

Acts

Runs the interview, transcribes it, scores each competency and writes the scorecard to the ATS.

05

Escalates

Sends borderline candidates and any accessibility or language issue to the recruiter with the recording.

06

Learns

Adjusts rubric and prompts from recruiter overrides, with the talent team, every sprint.

KPI it moves

Measured, with the source.

Every figure has a row in the Proof Ledger: source, date, owner and client permission.

Proof Ledger
Measured

Measured

1,000 per month to 1,000 per hour

Interview throughput

AI Interviewer case, Proof Ledger Sep 2026

Before

1,000 per month

After

1,000 per hour

Measured

720x

Throughput multiplier

AI Interviewer case, Proof Ledger Sep 2026

Measured

$0.035

Voice cost per 15-minute call

DaCodes voice stack, 15-minute call, internal measurement, Aug 2026. Stack cost, not a client result

Reviewed September 3, 2026

How it is governed

Every action has an owner, an eval and a limit.

Set in the Blueprint, enforced by the Govern layer of the platform.

Govern · Approval queue
Demo data

Waiting for a person

Borderline candidate on availability · the recruiter decides

Application 2291 · recording attached

Weekly eval

Passing

Score agreement with recruiters

93.8%

Last 8 runs
90.7% → 93.8%

Monthly sample · bias check by age band passed

Limit, enforced

Fourth call to application 2291 blocked

Human approvals

  • Interview guide and rubric approved by the talent team before go-live
  • Rejections are never sent automatically; the recruiter decides

Typical evals

  • Score agreement with recruiters on a monthly sample
  • Question coverage: every must-have asked in every call

Limits

  • No questions outside the approved guide
  • Personal data stays in your ATS; nothing trains a public model

Time to production

8 to 12 weeks

of pilot to production under a KPI Contract, after a Blueprint of 1 to 2 weeks

2 to 4 weeks of tuning inside the pilot, mostly on your roles and rubric. On Reclutalia the ATS side is already built, so most of the time goes to your interview guides.

DaCodes delivery standard, Sep 2026. Integration is the long pole, not the model.

How we deploy
The four phases
Commitment gate

  1. 01Discovery Express

    2 sessions, no cost

  2. 02Blueprint

    1 to 2 weeks

  3. 03Pilot

    8 to 12 weeks

  4. 04Scale & Managed

    Continuous

  • Pilot, first 8 weeks
  • Up to week 12 of the pilot
  • This agent: 2 to 4 weeks of tuning, inside the pilot
  • Commitment gate: the KPI decides Scale

Proof and demo

What backs the label.

Related agents

Same function or industry.

All agents
A new employee receiving a laptop at an IT service desk on her first day
In production

People & talent

Onboarding Agent

KPI it movesMeasured

Ready to work on day one

FAQ

Direct answers.

No. Reclutalia packages the ATS and the interviewer together, but the agent also writes to Workable and other ATS through their APIs. If you already have an ATS, we keep it as the system of record.

The voice stack runs on our own speech and language models, so it scales horizontally without per-minute vendor fees. In the AI Interviewer case that took a team from 1,000 calls a month to 1,000 an hour, at $0.035 of voice cost per 15-minute call.

Every candidate gets the same guide, the same rubric and a recruiter who makes the final call. We run bias checks on scores by gender and age band during the pilot and share them with your talent team.

Yes. It interviews in the candidate's language and writes the scorecard in the recruiter's language.

Which process do we automate first?

Two discovery sessions, no cost, and you leave with two or three quick wins whether or not you build with us.

We reply in under one business day.

Loading the form