4. Investor & Yield Desk

A self-serve desk for HNI and institutional investors: modelled yields, audited comps, exit scenarios and on-demand performance packs, with an agent answering portfolio questions in plain language. Target: Diligence pause cut from six weeks to one, repeat investment up.

Core buildConceptNext

Business impact

79/100

Investor deal cycle

Build effort

50/100

Customer-facing

Projected lift

+20%vs pre-agent baseline

Investor deal cycle

Time to value

2 quarters

From kickoff

Interactions / month

4,116+18%

Agent-handled

Automation rate

75%-6% human touches

No human in loop

Net value / year

₹2.5Cr

Revenue + cost avoided − run cost

Payback

9 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 investor deal cycle is produced

  • Eligible interactions4,727
  • Agent-handled3,62777%
  • Qualified outcome1,77749%
  • Investor deal cycle won66738%

Usage by geography

127
123
121
250
185
AhmedabadGandhinagarBengaluruPuneNRI - USA/GCC

Cost mix

Share of run cost

50
  • Inference39%
  • Integration27%
  • Data prep26%
  • Change mgmt20%

Cohort retention

Share of users still using the product weekly

W1W2W3W4W6W8
Cohort 11009484797261
Cohort 21049482746358
Cohort 31029679716052
Cohort 41019985816958
Cohort 51019886746354

Performance by geography

Indexed 0–100 across five signals

VolumeAccuracyDeflectionCSATRevenue
Ahmedabad4040834137
Gandhinagar82841009181
Bengaluru7074587996
Pune10038823578

Model quality

Live vs target

MetricCurrentTarget30-dayStatus
Precision9390+3.1On target
Recall8785+4.4On target
Grounded-answer rate8995+1.8Closing gap
Escalation rate86-2.2On target
P95 latency (s)43-0.4On target
Hallucination flags / 1k11-0.9On target

Service levels

79%

Impact score

50%

Delivery ease

97%

Uptime (30 days)

Unit economics

₹ per year, indexed to pilot scale

  • Revenue influenced₹2.3Cr
  • Cost avoided₹80L
  • Run cost₹26L
  • Net value₹2.5Cr

Cumulative ROI by quarter

Q1121% peakQ4

Channel mix

  • Voice17%
  • WhatsApp24%
  • Web10%
  • Field app23%
  • Email26%

Language mix

5
  • English28%
  • Hindi33%
  • Gujarati20%
  • Kannada29%
  • Marathi18%

Segment performance

Volume, automation and win rate per market

MarketInteractionsAutomationInvestor deal cycleValueTrend
Ahmedabad927
58%
23%₹30L
t0t1t2t3t4t5t6t7
Gandhinagar663
76%
20%₹25L
t0t1t2t3t4t5t6t7
Bengaluru981
65%
19%₹22L
t0t1t2t3t4t5t6t7
Pune690
60%
32%₹21L
t0t1t2t3t4t5t6t7
NRI - USA/GCC545
57%
39%₹20L
t0t1t2t3t4t5t6t7

Experiment log

What we tested on this product

ExperimentStatusResultOwner
Prompt v3 vs v2Won+8% investor deal cycleAiera Labs
Voice-first vs chat-firstRunning+3% so farGrowth Pod
Retrieval window 8k → 32kWon-3% escalationsPlatform
Human review threshold 0.7Rolled backno liftOps
Vernacular tone packRunning+7 CSAT ptsCX

Risk register

Owned mitigations before scale

RiskSeverityMitigationOwner
Data freshness in source systemsMediumHourly sync + staleness alertsData Eng
Regulatory language in outputsHighRERA registration numbersCompliance
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

  • SAP finance

    Actual collections, distributions and asset-level P&L

    Live

  • Data warehouse

    Single source for IRR, NPV and version deltas

    In build

  • KYC / AML providers

    Investor onboarding and compliance checks

    Planned

Product brief

Who uses it

Yield investors, family offices, IR team

Metric it moves

Investor deal cycle

Why Arvind wins

Institutional-grade transparency from a developer

Finance engineNarrative generationSecure investor portal

Guardrails

Applied to every response

  • RERA registration numbers
  • No assured-return claims
  • Broker attribution rules
  • 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 investor deal cycle 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, Residential and geography.

02

Ground the context

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

03

Reason and decide

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

04

Act in the workflow

Secure investor portal 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 investor deal cycle 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, Broker network, Portals, Site walk-in transcripts with intent, objection and sentiment labels.

    Streaming

  • Catalogue & pricing

    Residential · Commercial · Services 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

    Yield investors, family offices, IR team hits the moment this product exists for — diligence pause cut from six weeks to one, repeat investment up

  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 registration numbers, 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 investor deal cycle is attributed to this product.

Metric tree

What we steer and what we protect

North star

Investor deal cycle

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 registration numbers
  • 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
Customer-facing
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 Residential

Rollout waves

Scope and the exit test for each wave

Wave 1 — Prove

Ahmedabad, Residential, human review on every output.

Exit test: Investor deal cycle beats manual baseline on 200+ conversations.

Wave 2 — Automate

Add Gandhinagar 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 Real Estate
  • Approved language pack for English, Hindi, Gujarati, Kannada, Marathi
  • Telephony numbers and consent records for outbound
  • Sign-off on RERA registration numbers
  • 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 Residential?
  • What confidence threshold is acceptable before the agent acts unattended?
  • Which existing report does investor deal cycle get compared against?
← Back to portfolio