5. Household Intent Graph

Portal, ad, call, WhatsApp and walk-in signals resolved to one household with a live intent score, so the tele-calling desk works the right fifty families each morning instead of the newest two hundred. Target: Cost per site visit down 30% with the same media spend.

Core buildPrototypeNext

Business impact

87/100

Contact-to-visit rate

Build effort

48/100

Internal platform

Projected lift

+22%vs pre-agent baseline

Contact-to-visit rate

Time to value

2 quarters

From kickoff

Interactions / month

4,116+15%

Agent-handled

Automation rate

70%-6% human touches

No human in loop

Net value / year

₹0L

Revenue + cost avoided − run cost

Payback

7 months

Cumulative net positive

Adoption curve

Agent-handled volume vs pre-agent baseline

Jul98 peakDec

Baseline (manual process)

JulAugSepOctNovDec

Readiness scorecard

Six delivery dimensions

DataModelIntegrationAdoptionComplianceOps readiness

Outcome funnel

How contact-to-visit rate is produced

  • Eligible interactions4,272
  • Agent-handled3,37279%
  • Qualified outcome1,52245%
  • Contact-to-visit rate won63242%

Usage by geography

-64
28
74
97
-22
AhmedabadBengaluruPuneSuratNRI - GCC

Cost mix

Share of run cost

48
  • Inference34%
  • Integration8%
  • Data prep4%
  • Change mgmt3%

Cohort retention

Share of users still using the product weekly

W1W2W3W4W6W8
Cohort 11019489806858
Cohort 21069280766554
Cohort 31089280705652
Cohort 41079882767258
Cohort 51019586746755

Performance by geography

Indexed 0–100 across five signals

VolumeAccuracyDeflectionCSATRevenue
Ahmedabad5741389339
Bengaluru8066476442
Pune5674626683
Surat81907783100

Model quality

Live vs target

MetricCurrentTarget30-dayStatus
Precision8290+3.1Closing gap
Recall7585+4.4Closing gap
Grounded-answer rate8595+1.8Closing gap
Escalation rate06-2.2Closing gap
P95 latency (s)03-0.4Closing gap
Hallucination flags / 1k01-0.9Closing gap

Service levels

87%

Impact score

52%

Delivery ease

86%

Uptime (30 days)

Unit economics

₹ per year, indexed to pilot scale

  • Revenue influenced₹1.9Cr
  • Cost avoided₹37L
  • Run cost₹-11L
  • Net value₹0L

Cumulative ROI by quarter

Q194% peakQ4

Channel mix

  • Voice35%
  • WhatsApp27%
  • Web43%
  • Field app-20%
  • Email14%

Language mix

5
  • English-15%
  • Hindi-4%
  • Gujarati-13%
  • Kannada-18%
  • Marathi-20%

Segment performance

Volume, automation and win rate per market

MarketInteractionsAutomationContact-to-visit rateValueTrend
Ahmedabad-324
43%
8%₹-23L
t0t1t2t3t4t5t6t7
Bengaluru-412
49%
-1%₹-42L
t0t1t2t3t4t5t6t7
Pune-6
52%
8%₹-51L
t0t1t2t3t4t5t6t7
Surat197
33%
-1%₹-56L
t0t1t2t3t4t5t6t7
NRI - GCC298
24%
-6%₹-18L
t0t1t2t3t4t5t6t7

Experiment log

What we tested on this product

ExperimentStatusResultOwner
Prompt v3 vs v2Won+12% contact-to-visit rateAiera Labs
Voice-first vs chat-firstRunning+1% so farGrowth Pod
Retrieval window 8k → 32kWon-1% escalationsPlatform
Human review threshold 0.7Rolled backno liftOps
Vernacular tone packRunning+2 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

  • Housing / 99acres / MagicBricks

    Portal lead feeds with source and listing context

    Live

  • Google & Meta Ads APIs

    Click identity plus offline conversion upload

    Live

  • DeployOne Connect call data

    Intent, objection and sentiment per conversation

    Live

  • Salesforce CRM

    Score write-back and daily call list

    Live

Product brief

Who uses it

Sales heads, tele-calling desk, performance marketing

Metric it moves

Contact-to-visit rate

Why Arvind wins

Cross-channel identity across portals, ads and site visits that no single platform sees

Identity resolutionIntent scoringBudget feedback loop

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 contact-to-visit rate 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

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

03

Reason and decide

Intent scoring scores the situation and picks the next best action — answer, quote, schedule, escalate — with a confidence threshold behind it.

04

Act in the workflow

Budget feedback loop 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 contact-to-visit rate 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

    Sales heads, tele-calling desk, performance marketing hits the moment this product exists for — cost per site visit down 30% with the same media spend

  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 contact-to-visit rate is attributed to this product.

Metric tree

What we steer and what we protect

North star

Contact-to-visit rate

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

    0.5 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
Internal platform
Cost drivers
Inference volume, telephony minutes, integration upkeep
Charge basis
Per market licence + usage
Break-even
4 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: Contact-to-visit rate 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 contact-to-visit rate get compared against?
← Back to portfolio