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.
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.
Start where value and feasibility intersect. Tags mark the lighthouse, the fastest path to production, and the plays partners lead.
| Use case | Value | Feasibility | Speed | Note |
|---|---|---|---|---|
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 |
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.
Agent Platform correlates network + billing + subscriber context, runs conversations at spike scale, and executes grace/booking actions.
The telco's CC stack (GECX or incumbent) receives non-outage escalations and retention conversations; GECX leads CC-modernization tracks.
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.
Retention offers above policy, regulatory complaints, and field dispatch exceptions stay human-approved.
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.
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.
| Dimension | Conventional operating model | Point solutions / partial automation | Agentic model on Google Cloud + Tilicho Labs |
|---|---|---|---|
| Customer experience | Queue, IVR maze, repeat yourself at every step | One channel improves; experience breaks at its edges | Recognized, understood, and resolved in the customer's language on any channel |
| Process completion | Conversation ends; a human re-keys the outcome later, if at all | Bot deflects to forms or articles; completion still manual | Agent executes the transaction in systems of record within the conversation |
| Speed of response | Minutes of hold; days for follow-up | Instant answers for scripted intents only | Instant engagement and resolution for the majority of intents, 24/7 |
| Cost to serve | $13.50 median per assisted contact (Gartner 2024) | Savings on deflected volume; escalations still full cost | Self-service economics ($1.84 median, Gartner 2024) on contained volume; cheaper escalations via triage |
| Revenue & collections impact | Coverage-limited: uncontacted leads and accounts decay | Campaign blasts without conversation or negotiation | Every lead and account engaged in minutes, negotiated within policy |
| Context retention | None — each channel and call starts from zero | Session-scoped memory inside one tool | State and memory persist across channels, sessions, and handoffs |
| Personalization | Script-level segments at best | Rule-based greetings and merge fields | Grounded in the customer's actual history, entitlements, and intent |
| Multichannel continuity | Voice, chat, and email owned by different teams and vendors | Continuity only inside the vendor's channel | One agent layer: start on WhatsApp, continue on voice, finish by email |
| Human-agent productivity | Agents toggle 5–10 screens; after-call work eats capacity | Assist widgets bolt onto an unchanged workflow | Humans receive triaged, contextualized escalations with drafted next steps |
| Enterprise-system integration | Swivel-chair: humans are the integration layer | A few hard-wired API calls per bot | Governed tool-calling into CRM, core, ERP, ITSM — permissioned per interaction |
| Governance & compliance | 1–2% call sampling; script discipline is the control | Per-tool logs; no cross-channel policy enforcement | 100% of interactions logged, policy-checked in-line, and auditable |
| Scalability | Hire, train, attrite — capacity lags demand by months | Scales within one channel until intents get messy | Elastic on Google infrastructure; peak marginal cost ≈ flat |
| Measurement & improvement | QA samples and quarterly surveys | Vendor dashboard for its own slice | Every interaction evaluated against golden sets; policies and prompts improve weekly |
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
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
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
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
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
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
Channels and industry connectors are partner-built; the agent platform and models are Google Cloud; your systems of record and policies remain yours.
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.
Interaction arrives on any channel — or the enterprise initiates outreach
Identity and permissions resolved; consent and policy windows checked
Intent understood in the customer's language, with full context retrieved
Agent reasons over policies, history, and enterprise data
Governed actions executed in systems of record — payments, bookings, tickets, updates
Humans brought in on sentiment, complexity, or policy triggers — with full context
Outcome written back; 100% of the interaction logged and auditable
Every interaction evaluated; policies, prompts, and workflows refined
Defaults reflect typical telecommunications interaction profiles — replace them with yours. Every formula is shown; the pilot proves the containment rate before any scale decision.
Balance/plan/recharge intents on voice + WhatsApp for one circle/region, three languages