2. Drop & Allocation Intelligence

Predicts sell-through by SKU, size and city in week one and reallocates stock between stores, warehouses and marketplaces before markdown season decides for you. Target: Sell-through up 8-12 points before the first markdown.

Core buildConceptNow

Business impact

92/100

Full-price sell-through

Build effort

55/100

Internal platform

Projected lift

+23%vs pre-agent baseline

Full-price sell-through

Time to value

≤ 90 days

From kickoff

Interactions / month

3,906+10%

Agent-handled

Automation rate

73%-4% human touches

No human in loop

Net value / year

₹1.0Cr

Revenue + cost avoided − run cost

Payback

5 months

Cumulative net positive

Adoption curve

Agent-handled volume vs pre-agent baseline

Jul93 peakDec

Baseline (manual process)

JulAugSepOctNovDec

Readiness scorecard

Six delivery dimensions

DataModelIntegrationAdoptionComplianceOps readiness

Outcome funnel

How full-price sell-through is produced

  • Eligible interactions4,515
  • Agent-handled3,11569%
  • Qualified outcome1,66553%
  • Full-price sell-through won83550%

Usage by geography

19
-61
29
-56
32
Metro NCRMumbaiBengaluruHyderabadTier-2 cluster

Cost mix

Share of run cost

55
  • Inference43%
  • Integration14%
  • Data prep11%
  • Change mgmt1%

Cohort retention

Share of users still using the product weekly

W1W2W3W4W6W8
Cohort 11019386747059
Cohort 21049387766651
Cohort 31029580676048
Cohort 41059983757161
Cohort 51059282706153

Performance by geography

Indexed 0–100 across five signals

VolumeAccuracyDeflectionCSATRevenue
Metro NCR6370685893
Mumbai4468836641
Bengaluru9188796738
Hyderabad7838374495

Model quality

Live vs target

MetricCurrentTarget30-dayStatus
Precision8590+3.1Closing gap
Recall7585+4.4Closing gap
Grounded-answer rate8095+1.8Closing gap
Escalation rate66-2.2On target
P95 latency (s)13-0.4Closing gap
Hallucination flags / 1k-21-0.9Closing gap

Service levels

92%

Impact score

45%

Delivery ease

89%

Uptime (30 days)

Unit economics

₹ per year, indexed to pilot scale

  • Revenue influenced₹4.0Cr
  • Cost avoided₹44L
  • Run cost₹23L
  • Net value₹1.0Cr

Cumulative ROI by quarter

Q191% peakQ4

Channel mix

  • Voice87%
  • WhatsApp33%
  • Web-40%
  • Field app53%
  • Email-33%

Language mix

5
  • English-8%
  • Hindi0%
  • Tamil4%
  • Telugu6%
  • Bengali7%

Segment performance

Volume, automation and win rate per market

MarketInteractionsAutomationFull-price sell-throughValueTrend
Metro NCR-81
34%
-1%₹4L
t0t1t2t3t4t5t6t7
Mumbai159
24%
-6%₹12L
t0t1t2t3t4t5t6t7
Bengaluru-171
39%
6%₹16L
t0t1t2t3t4t5t6t7
Hyderabad-336
47%
-2%₹-22L
t0t1t2t3t4t5t6t7
Tier-2 cluster32
51%
8%₹-1L
t0t1t2t3t4t5t6t7

Experiment log

What we tested on this product

ExperimentStatusResultOwner
Prompt v3 vs v2Won+7% full-price sell-throughAiera Labs
Voice-first vs chat-firstRunning+1% so farGrowth Pod
Retrieval window 8k → 32kWon-0% 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 outputsHighMarketing consentCompliance
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 / retail ERP

    Stock ledger, transfers and margin by style

    Live

  • POS across 1,300+ doors

    Daily sales by size, colour and door

    Live

  • Marketplace seller APIs

    Sell-through and price position on Myntra, Ajio, Amazon

    In build

  • WMS / 3PL

    Automated transfer orders and replenishment

    In build

Product brief

Who uses it

Merchandising, planning, supply chain

Metric it moves

Full-price sell-through

Why Arvind wins

Margin recovered at full price, where the money actually is

Early-signal forecastingAllocation optimiserMarkdown engine

Guardrails

Applied to every response

  • Marketing consent
  • Return-policy accuracy
  • No unverified discount claims

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 Metro NCR with human review on every output.

Weeks 7–10

Automate the loop

Hand full-price sell-through 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, Menswear and geography.

02

Ground the context

Early-signal forecasting indexes the 3 Arvind product sets, pricing rules and policy language so nothing is answered from memory alone.

03

Reason and decide

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

04

Act in the workflow

Markdown engine 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 full-price sell-through 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, Store CRM, Marketplace, D2C site transcripts with intent, objection and sentiment labels.

    Streaming

  • Catalogue & pricing

    Menswear · Womenswear · Accessories & footwear 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

    Merchandising, planning, supply chain hits the moment this product exists for — sell-through up 8-12 points before the first markdown

  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 Marketing consent, 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 full-price sell-through is attributed to this product.

Metric tree

What we steer and what we protect

North star

Full-price sell-through

Drivers

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

Guardrail metrics

  • Grounded-answer rate above 95%
  • Escalation rate inside agreed band
  • Marketing consent
  • 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
6 months at pilot volume
Scale unit
One geography × one Menswear

Rollout waves

Scope and the exit test for each wave

Wave 1 — Prove

Metro NCR, Menswear, human review on every output.

Exit test: Full-price sell-through beats manual baseline on 200+ conversations.

Wave 2 — Automate

Add Mumbai 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 Fashions
  • Approved language pack for English, Hindi, Tamil, Telugu, Bengali
  • Telephony numbers and consent records for outbound
  • Sign-off on Marketing consent
  • Named market champions for floor adoption

Open questions for the business

Answer these to lock the scope

  • Which Metro NCR team runs the pilot and who signs off on outcomes?
  • How far back does usable conversation history go for Menswear?
  • What confidence threshold is acceptable before the agent acts unattended?
  • Which existing report does full-price sell-through get compared against?
← Back to portfolio