ThailandHealthcare / hospital networkLaunch · $50K
BDMS (Bangkok Dusit Medical Services)

Fifty hospitals, patients from a hundred countries: multilingual appointment and care coordination for BDMS

Deploy an agentic appointment and international-patient coordination layer across BDMS brands — booking, preparation, and follow-up in the patient's language, with every clinical question routed to qualified staff.

Entry use case
Appointment booking, reminders & preparation
Expected outcome
Reduce no-shows and call-queue friction across flagship hospitals while capturing international-patient inquiries 24/7 in their own languages
Recommended next step
Scope an appointment-and-reminder pilot at one flagship hospital plus a 24/7 international-inquiry agent for the Middle East desk.
What we understand

BDMS (Bangkok Dusit Medical Services)'s operating reality

BDMS is one of Asia-Pacific's largest private hospital groups with roughly 50 hospitals across brands including Bangkok Hospital, Samitivej, BNH, Phyathai, and Paolo, plus a significant medical-tourism business.

Public fact

International patients — Middle Eastern, Chinese, Japanese, expat — are a high-revenue segment requiring language-specific coordinators whose capacity gates inquiry response times.

Reasoned inference

Appointment no-shows and phone-only booking friction are standing costs across specialist clinics at every large hospital network.

Reasoned inference

Thailand's PDPA treats health data as sensitive, and clinical-safety governance requires that agents never give medical advice — routing design is the trust foundation.

Public fact

Post-discharge follow-up conversations (medication reminders, wound-care check-ins with photo escalation) could become a differentiated care product for BDMS's premium positioning.

Seller hypothesis — validate

Validate with the account team before outreach: HIS scheduling API accessibility across hospital brands · International-inquiry volume and current response-time baseline · Clinical-governance requirements for conversational AI in patient contact

Build vs buy

Why we have a right to win here

Buy-led target

Limited internal ability or appetite to build the core platform — strong candidate for the packaged solution

Evidence: BDMS is a hospital operator whose IT capacity is committed to clinical systems (HIS/EMR) and procured through healthcare vendors — there is no internal AI-platform organization, and none is plausible. Conversational infrastructure will be bought, with clinical governance as the selection criterion.

Why they won't build the full stack: Sensitive health data under Thai PDPA and strict no-medical-advice guardrails demand a hardened, auditable platform; an internal build would put clinical-governance risk on hospital IT teams that have no mandate for it.

What management is signalling

International-patient revenue growth and hospital-network expansion are recurring themes in investor communications.

Inferencerecent investor communications (validate) · 2025

GTM implication: One recovered international case pays for weeks of usage — position 24/7 multilingual intake as revenue capture, with no-show reduction as the domestic kicker.

What already exists (don't pitch this)
  • Hospital-brand apps and LINE Official Accounts
  • International patient coordinators by language desk
  • Per-hospital call centers and booking lines
  • HIS scheduling systems across brands
What customers still can't do end-to-end (pitch this)
  • →24/7 multilingual inquiry intake outside coordinator shifts
  • →Booking grounded in live HIS schedules across brands
  • →Platform-grade no-medical-advice guardrails with routed escalation
  • →Proactive reminders, preparation, and post-visit follow-up
Opportunity map

Where agentic communications pays off first

WorkflowWhy it matters hereValueComplexitySpeedChannels
Appointment booking & preparation
Booking against live schedules in Thai/English/Arabic/Mandarin, smart reminders with one-tap reschedule, prep instructions delivered proactively.
Specialist slot utilization and no-show rates directly drive revenue per bed and physician satisfaction.
Friction today: Phone-only booking with hold queues; reminders inconsistent across hospital brands.
LINEVoiceWhatsApp
International patient inquiry & coordination
24/7 multilingual intake, estimate and visa-letter process guidance, coordinator handoff with full context.
Each converted international case is high revenue; response speed in the inquirer's language decides conversion.
Friction today: Language coordinators cover business hours; inquiries from other timezones wait overnight.
WhatsAppEmailWeb chatVoice
Post-visit follow-up & billing questions
Itemized billing explanation within policy, aftercare instructions resent on demand, clinical questions routed to nurses.
Billing confusion and unclear aftercare drive repeat calls and erode premium perception.
Friction today: Patients call the ward or billing desk; answers depend on who picks up.
LINEVoice
Watch the change

Appointment booking, reminders & preparation: today vs the agentic model

Scenario: A patient in Riyadh inquires about a Samitivej health-checkup package at midnight Bangkok time; the agent answers in Arabic, shares the package estimate process, and books a teleconsult with the international desk for the morning.
Today
same interaction, two worlds
Agentic layer
No-show reduction
—
measured in pilot
Assumption
Cost per contact
$13.50 median assisted
$1.84 median self-service
Benchmark
QA coverage
1–2% sampled
100% scored
Platform capability
Sources & assumptions
  • · No-show reduction: Reminder-driven reductions vary by specialty; baseline first
  • · 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
LINEVoiceWhatsAppEmailWeb chat

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 · BDMS (Bangkok Dusit Medical Services)
HIS schedulingPatient CRMInternational patient CRMEstimate systemsBillingHIS

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

Trust & languages
ThaiEnglishArabicMandarinJapanese

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 interactions600K
Seller assumption — replace in discovery
Current cost per interaction ($)$1.6
Industry benchmark scale — validate
Automation / assistance rate (%)55%
Seller assumption — pilot proves this
$960K
Current operating cost / mo
$5.0M
Modelled gross benefit / yr
0.1 mo
Payback on Launch
352%
3-yr ROI (modelled)
Automated/assisted interactions per month330K
Modelled AI run-cost per month (usage + cloud, system estimate)$115K
New monthly operating cost$548K

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 BDMS (Bangkok Dusit Medical Services)'s measured baseline. Package price covers implementation only; recurring usage billed separately.

Recommended package

Launch — $50K implementation

Launch · $50K · A focused, fast production pilot8–10 weeks to a live, measured pilot

Why this package for BDMS (Bangkok Dusit Medical Services): A contained pilot on appointment journeys at one or two flagship hospitals respects clinical-governance review while proving no-show and call-deflection economics quickly.

Included
  • Up to 3 channels
  • One priority workflow
  • Limited enterprise integrations (1–2 systems)
  • API credential & security setup
  • Core conversational + workflow configuration
  • Basic analytics
  • Controlled production pilot with defined success criteria
Not included
  • ✕Usage & consumption (billed separately)
  • ✕Additional workflows
  • ✕Multi-geography rollout
  • ✕Managed operations
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: HIS scheduling, Patient CRM, International patient CRM
  • · A named business owner for appointment booking, reminders & preparation
  • · Security review counterpart and policy sign-off (HIS scheduling scope)
  • · Baseline metrics for the pilot's success thresholds
Executive messages

What to say to whom

CEO

“BDMS competes globally on clinical excellence wrapped in service excellence. Answering a Riyadh inquiry in Arabic at midnight is service excellence no staffing roster can deliver — and it books revenue.”

CIO / CTO

“One platform integrated with HIS scheduling serves every brand's appointment journey — governed centrally, with health-data handling designed for PDPA's sensitive-data class.”

COO

“No-show reduction and call deflection at flagship hospitals are measurable within one quarter — and the same platform absorbs the international-inquiry queue overnight.”

Chief Medical Officer / Head of International Services

“The agent never practices medicine: every clinical question routes to qualified staff with full context. What it does do is ensure no patient waits on hold to be cared for administratively.”

Chief Risk / Compliance Officer

“Sensitive-data consent, strict no-medical-advice guardrails, and complete interaction logs — clinical governance reviews a designed system, not an improvised chatbot.”

CFO / Procurement

“One recovered international case pays for weeks of platform usage; no-show reduction at specialist clinics compounds on top. The Launch package keeps initial exposure contained.”

Outreach

Pre-built offer emails for BDMS (Bangkok Dusit Medical Services)

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 3 — longer-term / partner-led

Why this tier

Southeast Asia's largest private hospital network (~50 hospitals: Bangkok Hospital, Samitivej, Phyathai, Paolo) with a major international-patient business — high-value appointments and multilingual coordination, but healthcare procurement cycles and clinical-safety review make it a patient, focused pursuit.

Recommended next step

Scope an appointment-and-reminder pilot at one flagship hospital plus a 24/7 international-inquiry agent for the Middle East desk.

Entry: Appointment booking, reminders & preparation · Launch package · 8–10 weeks to a live, measured pilot. 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.