Skip to content
Awaaz / V1
Live in 3 tenants

Fifteen thousand
applicants.
One shortlist,
in days.

Awaaz is the hiring control room for high-volume recruiters. A four-stage AI funnel screens CVs, runs anti-cheat assessments, scores written work, and conducts a live voice interview with each finalist. At a variable cost of about PKR 8.59 per candidate.

See the funnel
Funnel cycle11 days
Cost / candidatePKR 8.59
LanguagesEN · اردو
Live pipeline / SDH × Japan
Streaming
01
CV screenRubric + RAG
14,982in queue
02
MCQ testAnti-cheat
4,319in queue
03
WrittenPlagiarism
1,086in queue
04
Voice interviewLLM agent
312in queue
Recent movest-0
  • AHM-3401Ahmed R.MCQ84
  • FTM-2218Fatima K.Written91
  • USM-9087Usman A.Voice78
LHE · 31.5204°N · 74.3587°EAll systems nominal
Edition 12.06 — built for operatorsNo.0001
In production · now
12 sparkline · rolling
Variable cost / candidate
PKR 8.59
Median turnaround
11d 04h
Anti-cheat events / mo
2,418
Live voice agents
12 / 12
02 / The Stack

An entire hiring system,
built around the recruiter.

Pipelines, agents, automations, scoring rubrics, anti-cheat, billing. Six surfaces that behave like one product. No tabs hidden inside tabs. No "AI" sprinkled on top of a CRM.

Six surfaces01Pipeline builder02Voice agents03Automations04Configuration05Anti-cheat06Cost ledger
01
Pipeline builder

Compose any funnel as a directed graph.

Drag stages onto the canvas. Pin rubrics, gates, and SLAs to each node. Versioned, with an audit log on every change, and dry-runnable on a sampled cohort before you commit.

02
Agents

Voice agents that conduct the interview, not read from one.

Screener / SDH-EN-01running
Interviewer / SDH-JP-02running
Scorer / rubric-v8idle
03
Automations

when stage = MCQ
and score ≥ 72
do advance, email,
schedule interview.

Trigger sequences in plain English or visual blocks. Idempotent retries, DLQ surfaced in the audit log, every send signed and traceable.

Fired today1,402↑ 12%
04
Configuration

Rubrics as JSON. Versioned. Reviewable.

rubric.field-eng.v8.jsonvalid
{
  "stage": "MCQ",
  "gate": { "score": >= 72 },
  "weights": { "skill": 0.6, "lang": 0.4 }
}
Rubricsv8
Templates12
Subdomains3
05
Anti-cheat

Catch the half percent who try.

Tab-switch, paste, secondary device, voice deepfake checks, copilot detection in written answers. Flags graded by severity, not boolean.

Severity histogram · last 24h
06
Cost ledger

Every token, transcript second, and SMS, attributed to a candidate.

Tenant-scoped Redis emitter flushes to Postgres every minute. Billing knows what it's billing. Recruiters know what they spent.

This cycle / SDH
LLM tokensPKR 36,402
Voice min.PKR 18,118
SMS / emailPKR 4,031
03 / The Operators

Four users.
Four scenes.
One product.

The candidate sees a calm single column on 4G. The recruiter sees dense tables and a command palette. The tenant admin sees a quarterly summary. Ops sees a terminal deck. Same product, scene-driven chrome.

2 / 4
Scene

Processes 200 candidates a day. Hates clicks. Lives in keyboard shortcuts.

Surface

Operator deck / desktop

Density

Dense tables · keyboard-first


  • Virtualized tables, sortable to 50k rows
  • Ctrl-K command palette for every primary action
  • Side-by-side scorecard + transcript
  • Bulk advance / reject with one keystroke
ops.awaaz.app / pipeline / SDH-JP
4,319 candidates·312 active
K
IDNameStageScoreFlag
AHM-3401Ahmed R.Voice88
FTM-2218Fatima K.Written91
USM-9087Usman A.MCQ73
AYS-1142Ayesha M.Voice95
BLL-5520Bilal S.CV68
ZNB-7733Zainab H.Written94
04 / The Numbers
Edition 12.06 — Awaaz

The trust ledger.

Q1 2026 / verified

Numbers in this section come from production telemetry, not a brochure. They update on release. Every write in Awaaz is signed, every action is attributed to a user, and every impersonation event carries a reason and an auto-expiring scope. The audit log is read-only by design.

Tenants live trend
3
PK · JP · KE
Candidates / cycle trend
14,982
median, last 6 cycles
Median funnel time trend
11d 04h
from CV to shortlist
Cost / candidate trend
PKR 8.59
variable, last quarter
Voice interviews trend
8,407
to date, LLM-conducted
Anti-cheat flags trend
0.41%
of MCQ sessions
Uptime, p99
99.96%
rolling 30 days
Audit events
all
every write, signed
Last verified · 12 May 2026 · against production telemetryTelemetry on
Trust posture
GDPR aligned
EU + UK data subjects
Row-level isolation
Postgres RLS, per tenant
Signed audit log
SHA-256 + hash chain
Reasoned impersonation
Required reason + auto-expire
05 / The Wiring

Plugs into the stack
you already trust.

First-class adapters for LLMs, voice, queues, vectors. Outbound webhooks signed with HMAC. Inbound automations through Zapier, n8n, Make, or a raw REST endpoint. If you have a CRM, it speaks to Awaaz in one config screen.

OpenAILLM
AnthropicLLM
ElevenLabsVoice
TwilioPSTN
LiveKitWebRTC
ClerkAuth
SupabasePostgres
QdrantVectors
RedisQueues
PrismaORM
Google CalendarSchedule
ZapierWorkflows
n8nWorkflows
MakeWorkflows
WebhooksCustom
SalesforceCRM
HubSpotCRM
SES / ResendEmail
SentryErrors
PrometheusMetrics
20+ integrations · maintained adaptersInbound + outbound · signed
Outbound

Push events to anywhere you want them.

  • Signed webhooks with replay protection
  • Event types: stage.advanced, score.computed, flag.raised
  • Per-tenant secrets, per-job filters
  • Dead-letter queue surfaced in audit log
POST /your-webhook200 OK · 142ms
// event · stage.advanced
{
  "event": "stage.advanced",
  "id": "evt_2k9f...",
  "tenant": "sdh",
  "candidate": "AHM-3401",
  "from": "MCQ",
  "to": "Written",
  "score": 84,
  "sig": "hmac-sha256:a3f9..."
}
Inbound

Trigger Awaaz from your own systems.

  • REST API + typed TypeScript SDK
  • Bulk candidate import, CSV or JSON
  • Career-page form builder, embeddable anywhere
  • Idempotency keys on every mutation
06 / Q&A

Real questions,
answered plainly.

No marketing prose. If the answer is "no" or "we're working on it", that is what you will see.

  • Awaaz screens a high-volume applicant pool through a four-stage AI funnel: CV screening with rubric + retrieval, MCQ assessment with anti-cheat, written assessment with plagiarism and copilot detection, and a live voice interview run by an LLM agent. It produces a final shortlist of high-confidence hires from ~15,000 applicants in roughly eleven days, at a variable cost of about PKR 8.59 per candidate.

Didn't see your question?

We answer all of them ourselves.

No marketing inbox, no ticket queue. A founder reads every note. Average reply time is under three hours during PKT working day.

Email a founder