CX Excellence Suite
›AI Voice Hiring
—
📍 Commute radius: of the office
🎯 Match threshold ≥
🕘 Calls · retry h
Candidate pipeline
Every uploaded resume is parsed and matched against the JD automatically.
| Candidate | Location | Distance | JD Match | Score | Status | Action |
|---|
Match = JD-fit score ≥ threshold and within the commute radius. Only matching candidates can be scheduled for the AI screening call — the first round before the hiring team meets them. Age/gender are parsed for record-keeping only and never scored.
🎙️
Interview
Screening channel
Ready. Click Start Screening Call and allow the mic. The AI interviewer will greet the candidate first.
Candidate scorecard
First-round AI screening result — feeds the hiring team's decision; not a final hiring call.
Resume + call insights
Highlights
Concerns
Transcript
⬇ A .txt copy was downloaded automatically.
Hiring analytics
Screening funnel for the active JD.
Recent candidates
| Name | City | Distance | Score | Outcome |
|---|---|---|---|---|
| No data yet. | ||||
›AI Voice Coach
Choose a practice call
Pick a customer persona and the training phase. Scoring adapts to the phase's targets.
Coach analytics
Agent practice performance — independent of hiring.
By phase
Team impact projection
If every below-target session in this data were lifted to its phase's QA target via the Evaluate → Coach → Train → Retest loop.
Recent sessions
| Persona | Phase | QA | Result |
|---|---|---|---|
| No sessions yet. | |||
🎧
Customer
⏱ First-response window: 10.0s — respond before it hits zero
Ready. Click Start Call and allow the mic. The guest will speak first — respond promptly.
Session Scorecard
💡 Coaching notes
Strengths
Focus next
Transcript
⬇ A .txt copy was downloaded automatically.
Personalized training plan
Pre-training baselineCoaching opportunities identified
Recommended microlearning
Modules shown here are placeholder titles for this demo — in production, these route to your real content/LMS and are assigned automatically.
Improvement report
By coaching dimension — before → after
›LMS Learning
My Learning
Self-paced · Interactive course
0% COMPLETE
›AI Auto-QA
Score a call
Paste a call transcript, or load a sample. Scored against the active industry's rubric, with compliance fatals.
›Improvement Loop
Operational value
Your assumptions, your numbers. Edit anything on the left.
›Trainer
Trainer sign-in
Select your name to see your own batch dashboard.
Demo-only identity select — no password. Production would use real trainer accounts via SSO/roster, scoped so each trainer only ever sees their own batches.
My batches
Your NHT batches, practice trend, and how they carried into production.
My batch avg practice score — month on month
My batches
Click a batch to see its trainees.
| Batch | Start | Certified | Size | Avg NHT score | Fatals /100 | Status |
|---|
My NHT → Production linkage
How your batches' practice scores carried into production QA after certification.
| Batch | Avg NHT score | Avg production score | Δ practice → production |
|---|
Batch
Trainees
Click a trainee to see their practice sessions by phase.
| Trainee | Sessions | Avg NHT score | Status |
|---|
Trainee
›Admin
Admin sign-in
Enter the trainer PIN to configure the demo.
Demo PIN: 0000
Admin Configuration
All settings below are editable and drive the live demo.
Phase KPIs & QA targets
Three lifecycle phases, each with its own targets. Edit any cell.
| Parameter | New Hire Training | Nesting 0–30 days | Production >30 days |
|---|
Fatal QA rule
Auto-fail conditions applied to every scored session.
If the agent does not respond within this many seconds of the customer's first line, the session is an automatic fail regardless of other scores.
NHT Batch Performance Dashboard
Batch-wise practice performance, month-on-month trend, and linkage to production results.
Batch, trainer, and production-linkage figures below are illustrative fixtures for this demo. A production build would pull batch rosters from your LMS and production QA from your live scoring pipeline.
Batch avg practice score — month on month
Average NHT practice score of batches started in each month.
Batch-wise average scores
| Batch | Trainer | Start | Certified | Size | Avg NHT score | Fatals /100 | Status |
|---|
NHT → Production score linkage
Same batch, compared: average practice score during NHT vs. average production QA score after certification.
| Batch | Trainer | Avg NHT score | Avg production score | Δ practice → production |
|---|
Trainer-wise KPI comparison
Each trainer's batches vs. the team average for this date range.
| Trainer | Batches | Avg NHT score | vs team | Avg production score | vs team |
|---|
QA rubric
The scoring standard for this industry. Weights must total 100. Compliance-fatal
competencies auto-fail the call regardless of every other score — change anything here and the
Auto-QA scorecard and Improvement Report move with it.
Job description
What resumes are matched against and what the AI interviewer screens for.
Screening rules
Radius + threshold decide who counts as a match and gets an AI screening call.
Location radius is applied alongside the JD-fit threshold — a candidate must clear both to count as a match. Calling window keyed to candidate-local time. Age/gender are parsed from the resume for record-keeping only, never scored.
Interview questions
Per-JD question set — the HR admin configures these for each JD; the AI interviewer weaves them in conversationally.
Recruiter voice & notes
Persona and special instructions for the AI recruiter.