ThailandBankingScale · $100K
Bangkok Bank

The biggest balance sheet in Thailand deserves better than an IVR: agentic service for Bangkok Bank

Give Bangkok Bank an agentic service layer — Bualuang retail service in Thai on LINE and voice, SME servicing, and cross-border support aligned to its ASEAN network — grounded in core systems with BOT-grade auditability.

Entry use case
Retail service & digital-banking support
Expected outcome
Deflect balance, transfer, PromptPay, and app-support contacts into grounded in-channel resolution, with measured queue relief on the Bualuang hotline
Recommended next step
Baseline Bualuang hotline contact classes for one quarter and scope a LINE-first retail-service pilot with core-banking grounding.
What we understand

Bangkok Bank's operating reality

Bangkok Bank is Thailand's largest bank by assets, with the leading corporate and SME franchise, an international network across ASEAN and beyond, and majority ownership of Indonesia's Bank Permata acquired in 2020.

Public fact

Its digital posture has been deliberately conservative relative to KBank and SCB: Bualuang mBanking is functional but the bank has not pursued attacker-style digital ventures, and it retains a large branch-anchored customer base.

Reasoned inference

A branch-anchored, older-skewing retail base generates disproportionate assisted-service volume — exactly the base where Thai-language voice automation and LINE service produce the largest deflection economics.

Reasoned inference

BOT market-conduct regulation and Thailand's PDPA impose documented-handling and consent obligations that make 100% interaction logging a supervisory asset.

Reasoned inference

The Permata relationship and ASEAN network create a plausible multi-market platform story: one conversational governance frame serving Thai and Indonesian operations.

Seller hypothesis — validate

Thailand's mounting household-debt supervision (responsible-lending rules) is raising the operational bar on collections conduct across all Thai banks.

Public fact

Validate with the account team before outreach: Core and payment-system API accessibility for grounding · Internal digital roadmap and where a partner platform fits it · Appetite for a Permata-linked multi-market platform frame

Build vs buy

Why we have a right to win here

Partner-led target

Technically capable but needs industry workflows, integration, acceleration, or managed operations

Evidence: Bangkok Bank has serious technology operations but no attacker-style build culture; its history is procuring bank-grade platforms and integrating them conservatively. A partner-led deployment with strong governance is squarely in its procurement pattern — a full internal build is squarely outside it.

Why they won't build the full stack: The bank's differentiation is corporate relationships and balance-sheet trust, not consumer software; building conversational infrastructure would mean competing for talent against KBank's KBTG and SCB's tech arms from behind. Buying with a partner converts its scale into deflection economics without that race.

What management is signalling

Results commentary has emphasized asset-quality vigilance amid Thailand's household-debt overhang and elevated credit costs across the sector, alongside continued technology investment.

Inferencerecent investor communications (validate) · 2025

GTM implication: Cost and conduct discipline dominate the narrative — position service automation as an efficiency-and-compliance play, not an innovation experiment.

What already exists (don't pitch this)
  • Bualuang mBanking and iBanking
  • Thailand's largest corporate/SME franchise
  • International ASEAN network including Bank Permata
  • Large branch network and contact center
  • LINE presence for customer communication
What customers still can't do end-to-end (pitch this)
  • →In-conversation actions in core systems
  • →Production-grade Thai voice automation
  • →Two-way fraud confirmation
  • →SME self-service with trade-system grounding
  • →Cross-channel context between branch, hotline, and app
Opportunity map

Where agentic communications pays off first

WorkflowWhy it matters hereValueComplexitySpeedChannels
Bualuang retail service & app support
Grounded answers and in-conversation actions in Thai on LINE, in-app, and voice; warm handoff with context for complex cases.
Bulk service volume from a branch-anchored base is the largest addressable cost pool in the bank.
Friction today: IVR trees and branch queues absorb balance, transfer, and PromptPay questions; app-support calls spike with every release.
LINEIn-app chatVoice
SME servicing & trade support
Proactive status and grounded answers on LINE/voice; document checklists tracked conversationally; RMs receive context-rich escalations only.
The SME and trade franchise is the bank's crown jewel; RM time spent on status queries is origination capacity wasted.
Friction today: Loan-status, trade-document, and FX questions flow through relationship managers by phone.
LINEVoiceEmail
Fraud-alert response & card controls
Two-way confirmation in-channel with instant block/reissue within policy and fraud-team escalation with context.
Thailand's scam epidemic is a regulator-level priority; two-way confirmation prevents losses and call spikes.
Friction today: One-way SMS alerts generate panicked inbound; blocking requires queue time.
SMSLINEVoice
Watch the change

Retail service & digital-banking support: today vs the agentic model

Scenario: A shop-owner in Chonburi asks on LINE why her PromptPay transfer hasn't landed; the agent answers from the payment switch in Thai, resolves it in-channel, and her trade-financing document checklist updates in the same thread.
Today
same interaction, two worlds
Agentic layer
First-contact resolution
deferred via tickets
in-conversation actions
Platform capability
Cost per contact
$13.50 median assisted
$1.84 median self-service
Benchmark
QA coverage
1–2% sampled
100% scored
Platform capability
Sources & assumptions
  • · First-contact resolution: Process design: agent acts in systems of record
  • · Cost per contact: Gartner customer service cost benchmarks, 2024
  • · QA coverage: Platform capability: every interaction logged and evaluated
  • · 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
Recommended solution

One integrated stack, opinionated for this account

Channels · Tilicho Labs
LINEIn-app chatVoiceEmailSMS

Voice & channel orchestration, telephony, conversational execution, session/state, routing, integration build. Capability coverage validated during implementation.

Intelligence · Google Cloud
Gemini reasoningEnterprise groundingWorkflow agentsMulti-agent orchestrationGoverned actionsEvaluation & analytics
Systems · Bangkok Bank
Core bankingDigital banking platformCRMLoan originationTrade finance systemsDocument managementFraud monitoringCard management

API access to these systems is the critical-path dependency.

Trust & languages
ThaiEnglishMandarin

Identity-bound sessions, policy-bounded actions, 100% audit logging, human approvals at defined points, in-tenant intelligence.

Business case

The economics, with your numbers

Addressable monthly interactions3.5M
Seller assumption — replace in discovery
Current cost per interaction ($)$1.0
Industry benchmark scale — validate
Automation / assistance rate (%)55%
Seller assumption — pilot proves this
$3.5M
Current operating cost / mo
$15.0M
Modelled gross benefit / yr
0.1 mo
Payback on Scale
185%
3-yr ROI (modelled)
Automated/assisted interactions per month1.9M
Modelled AI run-cost per month (usage + cloud, system estimate)$674K
New monthly operating cost$2.2M

All figures are modelling estimates from the labeled inputs above — nothing here is customer-provided yet. The pilot's first job is replacing these assumptions with Bangkok Bank's measured baseline. Package price covers implementation only; recurring usage billed separately.

Recommended package

Scale — $100K implementation

Scale · $100K · A multi-channel production deployment10–14 weeks to production across priority workflows

Why this package for Bangkok Bank: Retail service, SME servicing, and fraud-response workflows across LINE, in-app chat, and voice at Thailand's largest bank justify a multi-workflow Scale deployment; a Launch pilot would be dwarfed by volume immediately.

Included
  • 4–6 channels
  • 2–3 priority workflows
  • Multiple enterprise integrations
  • API credential & security setup
  • Advanced orchestration
  • Multilingual support
  • Agent Assist / human escalation
  • Production analytics
  • Expansion roadmap
Not included
  • ✕Usage & consumption (billed separately)
  • ✕Enterprise-wide governance build-out
  • ✕Multi-BU rollout
Recurring costs (separate from the package)

Packages cover implementation and integration only. Recurring costs are billed separately: Tilicho Labs platform usage (~$0.15/call-min indicative, usage only), Google Cloud consumption, telephony/carrier charges, managed operations, and support & optimization. No package includes unlimited usage.

Customer resources required
  • · API access + credentials for: Core banking, Digital banking platform, CRM
  • · A named business owner for retail service & digital-banking support
  • · Security review counterpart and policy sign-off (Core banking scope)
  • · Baseline metrics for the pilot's success thresholds
Executive messages

What to say to whom

CEO / President

“Bangkok Bank's franchise strength has never depended on being first to digital fashion — but service economics are now a balance-sheet question. An agentic layer modernizes the customer experience without betting the bank on an internal tech transformation.”

CIO / CTO

“One partner-delivered integration into core, payments, and card systems powers retail, SME, and fraud workflows — no attacker-style rebuild required, and BOT-aligned residency options from the start.”

COO

“The Bualuang hotline's bulk volume moves to grounded self-service in Thai; branches and RMs work judgment cases; app-release support spikes stop being staffing events.”

Head of Retail / SME Banking

“SME relationship managers get their selling hours back, and the retail base gets 24/7 Thai service on LINE — measured deflection, not promised deflection.”

Chief Risk / Compliance Officer

“BOT market-conduct rules and PDPA consent become enforced configuration with 100% logged interactions — a stronger evidentiary position than any sampled-QA operation.”

CFO / Procurement

“The largest service-cost base in Thai banking is the denominator; even conservative deflection rates produce first-year returns that clear any hurdle rate, priced on implementation plus usage.”

Outreach

Pre-built offer emails for Bangkok Bank

Written from this account's own research — the strategic signal, the capability gap, the entry workflow, and the modelled economics — not a mail-merge template. Pick the moment and the persona, edit anything, then copy or open in your mail client.

Moment in the deal
Cold outreach — no prior conversation
Who it's addressed to
Cares about: The workflow itself and its daily failure modes
Register
Length
Draft — edit freely before sending
Open in mail client

Customer-safe by construction: drafts are composed only from customer-facing fields. Account tier, build-vs-buy classification, priority score, internal routing, and partner-commercial detail are not inputs to the composer, so they cannot appear in a draft. Money figures are always framed as modelled from the customer's own volumes. Read before sending — you own what goes out.

The pursuit

Tier 2 — high-potential incubation

Why this tier

Thailand's largest bank by assets with the country's biggest corporate franchise, an international network spanning ASEAN (including majority-owned Permata in Indonesia), and a deliberately conservative digital posture — enormous service volume with less internal digital-attacker capability than KBank or SCB, making it more buy-disposed than its scale suggests.

Recommended next step

Baseline Bualuang hotline contact classes for one quarter and scope a LINE-first retail-service pilot with core-banking grounding.

Entry: Retail service & digital-banking support · Scale package · 10–14 weeks to production across priority workflows. Human fallback throughout; success thresholds agreed before build.

Start the pursuit

Research-based priority-account universe assembled from public information, market scale, communication volume, and solution fit. This is NOT an authoritative list of top Google Cloud customers; existing Google Cloud relationships are noted only where publicly reported. Validate every account with the account team before outreach.