Telecommunications

A billion conversations, one governed layer

Plan support, activations, network triage, retention, and collections at telco scale — millions of interactions a day, dozens of languages, with cost per interaction that finally matches ARPU reality.

See the pilot
The executive problem

Telcos run the highest interaction volumes of any industry at some of the lowest revenue per user. Serving a $2-ARPU subscriber with an $8 human call is structurally broken math.

The interactions are deeply data-backed — balance, plan, network status, recharge — exactly the profile agents resolve end-to-end.

Churn and collections are conversation problems: the operator that reaches the right subscriber with the right offer in the right language, at scale, wins the margin war.

Why now
  • ARPU pressure makes human-assisted service economics untenable for prepaid bases
  • 5G and fiber upsell requires proactive, personalized outreach at a scale tele-calling can't touch
  • Network-issue calls spike in storms and outages — exactly when human capacity is worst
  • Multilingual subscriber bases are underserved by monolingual IVR trees
7×
cost gap between assisted and self-service contacts ($13.50 vs $1.84) — untenable at prepaid ARPU
Gartner cost benchmarks, 2024
10+
languages a single agent deployment serves without staffing constraints
platform capability (Gemini + Chirp speech models)
30–40%
of telco call volume is balance, recharge, and plan queries
operator benchmarks; validate per customer
Priority use cases

Ranked by value, feasibility, and speed

Start where value and feasibility intersect. Tags mark the lighthouse, the fastest path to production, and the plays partners lead.

Use caseValueFeasibilitySpeedNote
Plan, billing & balance support
Lighthouse
Highest volume; clean BSS APIs; instant containment
Recharge reminders & collections
Fastest to production
Direct revenue; prepaid churn prevention
Churn prediction outreach & retention offers
Executive value
Offer matrix governance critical
Service activation & SIM/eSIM onboarding
KYC steps stay system-owned; agent orchestrates
Network issue triage & outage communication
Highest volume
Deflects storm-driven spikes; NOC data grounding
Technician scheduling & visit coordination
Field-service system integration; no-show reduction
Upsell & cross-sell (5G, fiber, OTT bundles)
Propensity-triggered, consent-governed
Multi-language inbound servicing
Long-tail languages human benches can't cover
Retail & field-agent assist
Partner-led
Store staff plan lookup, MNP handling
Enterprise (B2B) account servicing
Higher-value, lower-volume expansion
Lighthouse journey

Network issue triage, before and after

Today
  1. 1Outage hits; call volume spikes 5× while human queues melt down
  2. 2IVR knows nothing about the outage; customers wait 30 minutes to hear 'we're aware'
  3. 3Agents manually check NOC dashboards, give inconsistent restoration estimates
  4. 4No proactive communication; every affected subscriber who calls costs $5–8
  5. 5Post-outage, churn spikes in affected areas with no retention response
With the agentic layer
  1. 1Agent correlates the caller's location with live network status before saying hello
  2. 2Known-outage callers get restoration estimates and SMS/WhatsApp updates — in seconds, any language
  3. 3Genuine device or line faults get guided triage; unresolved cases book a technician directly
  4. 4Proactive outage notifications suppress the call spike before it forms
  5. 5Affected-area subscribers get automated post-restoration check-ins and retention offers
Watch the transformation

The same interaction, two worlds — racing live

The loop runs itself: the conventional journey stalls, backtracks, and drags while the agentic one flows straight through — grounding, acting, and resolving with a human approval exactly where policy demands one. Pause anytime and click any node to explore that step.

Scenario: A fiber outage hits a neighborhood; a prepaid customer's bill-date lands the same week
Today
same interaction, two worlds
Agentic layer
Outage call spike
5× normal volume
suppressed by proactive notice
Assumption
Languages served
2–3 staffed
10+ via one deployment
Platform capability
Cost per interaction vs ARPU
$13.50 assisted median
$1.84 self-service median
Benchmark
ETA consistency
per-agent guesswork
one authoritative feed
Platform capability
Churn save rate
—
measured in pilot
Assumption
Sources & assumptions
  • · Outage call spike: Spike multiple is an operator-reported pattern (assumption); suppression measured in pilot
  • · Languages served: Platform capability: Gemini + Chirp speech models
  • · Cost per interaction vs ARPU: Gartner 2024 benchmarks — the gap is untenable at prepaid ARPU
  • · ETA consistency: Process design: single source of truth
  • · Churn save rate: Depends on offer policy and base mix; baseline before projecting
  • · Gartner, customer service cost benchmarks (2024): $13.50 median assisted vs $1.84 self-service per contact
  • · McKinsey, digital-first collections research: 20–25% NPL reduction among leaders; up to 40% opex reduction with gen AI
  • · Baymard Institute: ~70% average cart abandonment (meta-analysis)
  • · IAMAI–Kantar via IBEF (2025): 900M+ Indian internet users; 98% consume Indic-language content
  • · LeadSquared and vendor funnel studies: 78% of students choose the first institution to respond (directional, vendor data)
  • · HDI / ITSM operator benchmarks: $15–25 per L1 ticket; 40–60% of L1 volume is resets/status (validate per customer)
  • · Conventional-flow wait times and volumes are typical operator patterns — assumptions to replace with the customer's own baseline
  • · Agentic-flow behaviors (context retention, 100% logging, in-line policy checks) are platform capabilities, not projections
One integrated solution — clear ownership
Gemini Enterprise Agent Platform

Agent Platform correlates network + billing + subscriber context, runs conversations at spike scale, and executes grace/booking actions.

Customer Engagement Suite (GECX)

The telco's CC stack (GECX or incumbent) receives non-outage escalations and retention conversations; GECX leads CC-modernization tracks.

Tilicho Labs — communications & implementation

Tilicho Labs provides carrier-grade call handling and channel infrastructure and integrates NOC feeds, BSS/OSS APIs, and regional-language coverage; deployment and optimization are managed services.

Human oversight

Retention offers above policy, regulatory complaints, and field dispatch exceptions stay human-approved.

Customer & employee impact

Customers: Told about the outage before noticing, in their own language, with an honest ETA — and never billed or barred for the operator's downtime.

Employees: Agents stop apologizing for information they don't have; field and retention teams work ranked, pre-diagnosed queues.

Value drivers · differentiators
Call-spike suppression at near-zero marginal costLanguage coverage without language staffingChurn prevention at the moment of riskBilling-assurance coordinationField-force efficiency from pre-diagnosisCarrier-scale elasticity on Google infrastructureNOC-to-CX real-time grounding10+ languages incl. code-switching in one deploymentIn-tenant subscriber data handling
Operating-model comparison

Conventional vs point solutions vs agentic

Thirteen dimensions where the operating models differ — from experience and speed to governance and measurement. Point solutions improve one channel; the agentic layer changes how the whole enterprise communicates.

Conventional: Queue, IVR maze, repeat yourself at every step

Point solutions: One channel improves; experience breaks at its edges

Agentic: Recognized, understood, and resolved in the customer's language on any channel

Who you'll talk to

Every stakeholder, one coherent story

CEO

Cares about: Margin per subscriber, churn

Wants: Service cost aligned to ARPU; retention at scale

Will object: We've spent millions on IVR already

Proof that works: Cost-per-interaction model on their own volumes

“What does it cost to serve your lowest-ARPU decile today, per contact?”
CTO

Cares about: BSS/OSS integration, scale, latency

Wants: Carrier-grade agent layer in their cloud

Will object: Nothing external touches our BSS

Proof that works: In-tenant architecture + load-tested reference deployment

“This runs inside your tenant and speaks to BSS through your own governed APIs.”
Customer Service leader

Cares about: Queue SLAs across languages

Wants: 70%+ containment on top intents, 24/7

Will object: Our intents are messier than you think

Proof that works: Conversation-intelligence audit of their real call data first

“Let's analyze a month of your calls before we automate anything.”
CMO

Cares about: Churn, upsell conversion

Wants: Two-way retention conversations, not SMS blasts

Will object: Outbound AI calls will annoy subscribers

Proof that works: Consent-governed pilot with opt-out and sentiment tracking

“Your win-back SMS gets 1% response. A conversation in the subscriber's language gets more.”
Collections leader

Cares about: Postpaid receivables, prepaid lapse

Wants: Every at-risk account contacted on day one

Will object: Regulatory limits on collections calls

Proof that works: Policy-window enforcement built into orchestration

“How many day-1 delinquents does your team actually reach?”
Architecture

The same layers, grounded in your systems

Channels and industry connectors are partner-built; the agent platform and models are Google Cloud; your systems of record and policies remain yours.

Gemini Enterprise Agent Platform

Enterprise Intelligence & Agents

Google Cloud provides the intelligence: agents that reason over policies, history, and enterprise data, coordinate specialized agents, and execute governed actions — running in the customer's Google Cloud environment.

Gemini reasoning & intentEnterprise grounding with citationsDomain & workflow agentsMulti-agent orchestrationEnterprise-system actionsPolicy enforcement & model routing
1Contact

Interaction arrives on any channel — or the enterprise initiates outreach

2Identify

Identity and permissions resolved; consent and policy windows checked

3Understand

Intent understood in the customer's language, with full context retrieved

4Reason

Agent reasons over policies, history, and enterprise data

5Act

Governed actions executed in systems of record — payments, bookings, tickets, updates

6Escalate

Humans brought in on sentiment, complexity, or policy triggers — with full context

7Record

Outcome written back; 100% of the interaction logged and auditable

8Improve

Every interaction evaluated; policies, prompts, and workflows refined

Economics

Model it with your numbers

Defaults reflect typical telecommunications interaction profiles — replace them with yours. Every formula is shown; the pilot proves the containment rate before any scale decision.

Your inputs
5.0M
3 min
$0.30
$0.05
65%
$250K
Modelled impact
$2.8M
monthly cost savings
0.1 mo
payback period
$101.7M
three-year net value
3.3M
interactions resolved by agents / month
Sensitivity — containment ±15 points
$2.4M
$3.2M
monthly savings range across containment scenarios
Assumptions & formulas (no hidden numbers)
  • Baseline cost = interactions × minutes × human $/min
  • Contained interactions cost AI $/min only; escalated interactions incur AI cost + 60% of human handle time (triage saves the rest)
  • Revenue uplift = contained volume × $0.4/resolved × 2% incremental outcome lift (conservative default — replace with pilot data)
  • Containment is the pilot's job to prove — the sensitivity band shows the stakes. These are modelling defaults, not claims.
Security & regulatory

Designed for your regulatory reality

TRAI / telecom-regulator consent and DND compliance enforced in orchestration
Calling windows, frequency caps, and opt-outs as platform policy, not script discipline
Subscriber data stays in-tenant; lawful-intercept and retention obligations unaffected
Offer governance: retention and upsell offers only from approved matrices
The pilot

Narrow scope. Real traffic. Explicit thresholds.

Scope · 8–12 weeks

Balance/plan/recharge intents on voice + WhatsApp for one circle/region, three languages

Integration boundary
BSS (read balance/plan)Recharge/payment gatewaySMSC/WhatsApp BSP via Tilicho Labs
Success is measured as
  • Containment on pilot intents
  • Cost per interaction vs blended human cost
  • CSAT / repeat-call rate
  • Recharge conversion on reminders
  • P95 latency at load
Expansion roadmap

One pilot, then the platform

1
All service intents
2
Churn & retention outreach
3
Network triage + proactive outage comms
4
Collections
5
B2B servicing
Common questions

Asked in every meeting