3. Channel Partner Transaction OS

Partners run their whole business on WhatsApp — live inventory, unit holds, client registration, documentation status and payout ledger — with attribution locked at first message. Target: 80% of partner queries closed without a channel manager, payout disputes near zero.

Quick winPilotNow

Business impact

84/100

Partner-sourced bookings

Build effort

34/100

Channel platform

Projected lift

+21%vs pre-agent baseline

Partner-sourced bookings

Time to value

≤ 90 days

From kickoff

Interactions / month

3,654+9%

Agent-handled

Automation rate

70%-6% human touches

No human in loop

Net value / year

₹2.1Cr

Revenue + cost avoided − run cost

Payback

11 months

Cumulative net positive

Adoption curve

Agent-handled volume vs pre-agent baseline

Jul87 peakDec

Baseline (manual process)

JulAugSepOctNovDec

Readiness scorecard

Six delivery dimensions

DataModelIntegrationAdoptionComplianceOps readiness

Outcome funnel

How partner-sourced bookings is produced

  • Eligible interactions4,212
  • Agent-handled3,21276%
  • Qualified outcome1,66252%
  • Partner-sourced bookings won73244%

Usage by geography

232
306
213
166
273
AhmedabadBengaluruPuneSuratNRI - GCC

Cost mix

Share of run cost

34
  • Inference46%
  • Integration35%
  • Data prep23%
  • Change mgmt20%

Cohort retention

Share of users still using the product weekly

W1W2W3W4W6W8
Cohort 11029383777058
Cohort 21079486766555
Cohort 31049380756352
Cohort 41039684776661
Cohort 51039680726552

Performance by geography

Indexed 0–100 across five signals

VolumeAccuracyDeflectionCSATRevenue
Ahmedabad8655845771
Bengaluru5055529894
Pune4265893670
Surat7268679848

Model quality

Live vs target

MetricCurrentTarget30-dayStatus
Precision8290+3.1Closing gap
Recall7985+4.4Closing gap
Grounded-answer rate9395+1.8Closing gap
Escalation rate96-2.2On target
P95 latency (s)33-0.4On target
Hallucination flags / 1k11-0.9On target

Service levels

84%

Impact score

66%

Delivery ease

86%

Uptime (30 days)

Unit economics

₹ per year, indexed to pilot scale

  • Revenue influenced₹2.9Cr
  • Cost avoided₹1.1Cr
  • Run cost₹28L
  • Net value₹2.1Cr

Cumulative ROI by quarter

Q1118% peakQ4

Channel mix

  • Voice26%
  • WhatsApp31%
  • Web15%
  • Field app11%
  • Email18%

Language mix

5
  • English24%
  • Hindi31%
  • Gujarati34%
  • Kannada21%
  • Marathi29%

Segment performance

Volume, automation and win rate per market

MarketInteractionsAutomationPartner-sourced bookingsValueTrend
Ahmedabad412
81%
39%₹46L
t0t1t2t3t4t5t6t7
Bengaluru406
68%
28%₹33L
t0t1t2t3t4t5t6t7
Pune853
81%
23%₹26L
t0t1t2t3t4t5t6t7
Surat626
68%
20%₹63L
t0t1t2t3t4t5t6t7
NRI - GCC513
61%
33%₹41L
t0t1t2t3t4t5t6t7

Experiment log

What we tested on this product

ExperimentStatusResultOwner
Prompt v3 vs v2Won+6% partner-sourced bookingsAiera Labs
Voice-first vs chat-firstRunning+5% so farGrowth Pod
Retrieval window 8k → 32kWon-6% escalationsPlatform
Human review threshold 0.7Rolled backno liftOps
Vernacular tone packRunning+5 CSAT ptsCX

Risk register

Owned mitigations before scale

RiskSeverityMitigationOwner
Data freshness in source systemsMediumHourly sync + staleness alertsData Eng
Regulatory language in outputsHighRERA disclosureCompliance
Field-team adoptionMediumIn-app nudges + weekly coaching drillsSales Ops
Model cost driftLowRouter to smaller models for routine intentsPlatform

Where it sits in the portfolio

Tap another dot to switch product

Quick winsBig bets
Impact ↑Effort →

Systems it touches

  • WhatsApp Business Platform

    Partner identity, templates and interactive flows

    Live

  • Salesforce CRM

    Client registration, dedupe window and attribution

    Live

  • SAP finance

    Brokerage accrual, invoice and payout status

    In build

Product brief

Who uses it

480+ channel partners, channel head

Metric it moves

Partner-sourced bookings

Why Arvind wins

Attribution and payouts in one system removes the disputes that lose partners

WhatsApp Business APIHold + registration enginePayout ledger

Guardrails

Applied to every response

  • RERA disclosure
  • No price commitment on call
  • DND scrubbing
  • Call recording consent

Delivery plan

14-week path to production

Weeks 1–3

Ground the data

Connect 3 product sets, historical conversations and CRM outcomes.

Weeks 4–6

Pilot with one team

Run in Ahmedabad with human review on every output.

Weeks 7–10

Automate the loop

Hand partner-sourced bookings decisions to the agent with escalation thresholds.

Weeks 11–14

Scale across lines

Roll out to 5 languages and all geographies.

How it works

End-to-end, from signal to learned outcome

01

Capture the signal

Every Voice and WhatsApp interaction, plus CRM and order events, is streamed in and tagged to a customer, Plotted development and geography.

02

Ground the context

WhatsApp Business API indexes the 3 Arvind product sets, pricing rules and policy language so nothing is answered from memory alone.

03

Reason and decide

Hold + registration engine scores the situation and picks the next best action — answer, quote, schedule, escalate — with a confidence threshold behind it.

04

Act in the workflow

Payout ledger writes back into CRM/ERP and fires the customer-facing action in English or Hindi, so the team sees it where they already work.

05

Learn from outcome

Won/lost and partner-sourced bookings outcomes flow back nightly; prompts, thresholds and routing are retuned every fortnight.

Data it runs on

Sources, contents and refresh cadence

  • Conversation history

    Voice, WhatsApp, Portal leads, Channel partners, Walk-in transcripts with intent, objection and sentiment labels.

    Streaming

  • Catalogue & pricing

    Plotted development · Villas & row houses · Apartments with specs, availability and approved commercial language.

    Hourly

  • CRM outcomes

    Stage moves, win/loss reasons and owner activity per enquiry.

    15 min

  • Operations systems

    ERP order, stock, dispatch and service records used to answer status questions.

    Hourly

  • Market signals

    Demand and competitor movement across 5 geographies via DeployOneSense.

    Daily

Customer & team journey

  1. 1Trigger

    480+ channel partners, channel head hits the moment this product exists for — 80% of partner queries closed without a channel manager, payout disputes near zero

  2. 2Agent acts

    Aiera responds within seconds on Voice, grounded in the live catalogue and the customer's own history.

  3. 3Human in the loop

    Anything below the confidence threshold, or touching RERA disclosure, routes to a named owner with full context attached.

  4. 4Close the loop

    Outcome is written back, the customer gets a summary on WhatsApp, and partner-sourced bookings is attributed to this product.

Metric tree

What we steer and what we protect

North star

Partner-sourced bookings

Drivers

  • Agent-handled share of eligible interactions
  • First-response time and resolution time
  • Qualified outcomes per 100 conversations in Ahmedabad
  • Repeat engagement within 30 days

Guardrail metrics

  • Grounded-answer rate above 95%
  • Escalation rate inside agreed band
  • RERA disclosure
  • Run cost per conversation below target

Squad to build it

Who is needed and for what

  • Product owner (Arvind)

    Scope, adoption and the business case

    0.3 FTE

  • Conversation designer

    Prompts, tone and 5-language scripts

    1 FTE

  • Data / integration engineer

    CRM, ERP and telephony wiring

    1 FTE

  • ML engineer

    Scoring models, evaluation harness, drift

    0.5 FTE

  • Ops champion per market

    Floor adoption across 5 geographies

    0.2 FTE each

Commercials

How the product pays for itself

Delivery model
Channel platform
Cost drivers
Inference volume, telephony minutes, integration upkeep
Charge basis
Per handled conversation
Break-even
6 months at pilot volume
Scale unit
One geography × one Plotted development

Rollout waves

Scope and the exit test for each wave

Wave 1 — Prove

Ahmedabad, Plotted development, human review on every output.

Exit test: Partner-sourced bookings beats manual baseline on 200+ conversations.

Wave 2 — Automate

Add Bengaluru and Hindi; agent acts without review above threshold.

Exit test: Escalation rate under 10% for four straight weeks.

Wave 3 — Extend

All 3 product sets and 5 channels, wired into CRM reporting.

Exit test: Adoption above 70% of eligible interactions.

Wave 4 — Compound

Roll across 5 geographies and share the model with sibling Arvind businesses.

Exit test: Net value positive at run-rate; owned by business-as-usual team.

Dependencies to unblock

Needed before wave 1 starts

  • API access to CRM and ERP for Arvind SmartSpaces
  • Approved language pack for English, Hindi, Gujarati, Kannada, Marathi
  • Telephony numbers and consent records for outbound
  • Sign-off on RERA disclosure
  • Named market champions for floor adoption

Open questions for the business

Answer these to lock the scope

  • Which Ahmedabad team runs the pilot and who signs off on outcomes?
  • How far back does usable conversation history go for Plotted development?
  • What confidence threshold is acceptable before the agent acts unattended?
  • Which existing report does partner-sourced bookings get compared against?
← Back to portfolio