Tilicho Labs
Cards, paylater, collections, KYC, insurance

Voice agents for financial services in Southeast Asia

AI agents that call and answer your customers on the phone, on WhatsApp and on web chat, in more than 25 languages. They finish the task during the conversation: take a promise to pay on a paylater instalment, activate a card, complete a KYC review, renew a policy. Tilicho builds and runs them inside your own Google Cloud project for banks, finance companies and insurers in Indonesia, Malaysia, Singapore, Thailand, Vietnam and the Philippines, starting from accelerators for 28 financial services use cases.

Paylater instalment, 5 days overdueBahasa Indonesia
Sample call
AgentCustomerSystems
Paylater record read: 3-month plan, instalment Rp1.250.000, due 25 Sep
AgentSelamat siang. Apakah saya berbicara dengan Ibu Dewi Lestari?
CustomerYa, saya sendiri.
Right person confirmed
AgentSaya asisten AI dari ABC Finance. Panggilan ini direkam. Cicilan paylater Ibu sebesar Rp1.250.000 jatuh tempo 25 September dan belum kami terima.
CustomerGaji saya baru masuk tanggal 1.
AgentBaik. Boleh saya catat Ibu akan membayar pada 1 Oktober?
CustomerYa, tanggal 1.
Logged in the paylater ledger: promise to pay Rp1.250.000 by 1 Oct
AgentTerima kasih. Link pembayaran saya kirim sekarang lewat WhatsApp. Saya tidak akan pernah meminta kode OTP atau PIN Ibu.
WhatsApp sent: payment link
Follow-up call scheduled: 1 Oct, 10:00 am, if unpaid
Card record read: purchase of RM3,600 on 21 Sep, eligible for a 0% plan
AgentSelamat petang. Boleh saya bercakap dengan Encik Hafiz Rahman?
CustomerYa, saya.
Right person confirmed
AgentSaya AI assistant dari ABC Bank. Call ini direkodkan. Your purchase of RM3,600 last week boleh ditukar ke 0% instalment plan.
CustomerKalau 12 bulan, berapa sebulan?
AgentRM300 sebulan for 12 months. 0% interest, tiada processing fee. Nak saya tukar sekarang?
CustomerOK, boleh. Go ahead.
Consent recorded with timestamp
Instalment request raised: RM3,600 over 12 months at 0%
AgentDone. Persetujuan Encik sudah direkodkan dalam call ini. Confirmation dan jadual bayaran saya hantar melalui WhatsApp.
WhatsApp sent: confirmation and payment schedule
Account record read: customer due-diligence review due by 31 Oct
AgentGood afternoon. Am I speaking with Ms Tan Mei Ling?
CustomerYes, speaking.
Right person confirmed
AgentI am the AI assistant from ABC Bank. This call is recorded. Your account is due for its periodic review by 31 October. It takes about five minutes in the app.
Customer我可以用华语吗?
Language switched to Mandarin
Agent可以。您只需要在App里确认地址和职业。如果有变更,可以直接上传文件。我现在通过WhatsApp发链接给您。我不会问您的密码或OTP。
WhatsApp sent: KYC review link
Customer好,今晚我来做。
Agent谢谢。如果链接有问题,可以打这个号码。
Tagged in CRM: link sent, customer will complete today
Completion check scheduled: 20 Oct. Second call only if still pending
Policy record read: comprehensive car insurance, premium ₱18,450, due 15 Oct
AgentGood morning po. Si Mr. Paolo Reyes po ba ito?
CustomerOo, ako 'to.
Right person confirmed
AgentAko po ang AI assistant ng ABC Insurance. Recorded po ang call na ito. Due na po for renewal ang car insurance ninyo sa 15 October. Ang premium po ay ₱18,450.
CustomerPwede bang i-add ang acts of nature? Binabaha kasi sa amin.
AgentNagbabago po ang premium kapag may dagdag na coverage, kaya isang advisor po ang mag-aasikaso. Ikokonekta ko na po kayo ngayon. Okay lang po ba?
CustomerSige.
Transferred to an advisor with the summary: renewal due 15 Oct, wants to add acts of nature cover
Tagged in CRM: transferred, change of cover requested
Names, amounts and dates are examples.
In production in
LendingReal estateHigher educationHealthcareE-commerceHome services
See the use cases
Comparison

Human calling team and voice agent

Human calling teamVoice agent
Calls in a dayAbout 100 per agent50,000+ across the campaign
First contactUp to 42 hours after the enquiryWithin minutes
LanguagesThe languages your team speaks25+, switching during the call
ScriptVaries by person and by dayThe approved script on every call
Follow-upDepends on the caller's notesScheduled until the outcome is reached
RecordA sample of calls is reviewedRecording, transcript and outcome tag on every call
CapacityHiring and training, with 30% leaving each yearAdded in a day, removed after the peak
Capabilities

What the agent can do

In conversation

  • Answers and places calls, 50,000+ in a day
  • Speaks 25+ languages and switches when the customer does
  • Stops when interrupted and picks up from there
  • Stays clear on a noisy line
  • Speaks with a natural tone and empathy, in a voice you choose
  • Remembers earlier calls and chats with the same customer

Actions during the call

  • Reads and updates the CRM, loan, card or policy record
  • Sends links, documents and confirmations on WhatsApp or SMS
  • Books slots: courier delivery, branch visit, advisor callback
  • Raises and updates tickets
  • Finds the nearest branch or ATM for the customer
  • Answers from your product documents and FAQs

Outbound campaigns

  • Campaigns from an uploaded list or from your CRM
  • Targeting by market, segment, bucket, product or due date
  • Retries for no-answers and scheduled callbacks
  • Automatic follow-ups until the outcome is reached
  • Answering machines and voicemail detected

After every call

  • Recording and full transcript
  • Summary with the key points and next actions
  • Customer sentiment
  • Outcome tag written to your system
  • Summary message to the customer and to your team

With your people

  • Live transfer with the transcript summary attached
  • Signs of distress route the call to a person
  • Approval from a supervisor on Slack while the caller holds
  • Callback booked for a named team member

Connected to your stack

  • Salesforce, HubSpot, Zoho, KaptureCX
  • Twilio, Plivo, Telnyx, Exotel, Genesys, SIP trunks
  • Zendesk, Freshdesk, Google Calendar, Calendly, Cal.com
  • 5,000+ more apps through Zapier
  • Any other system through its API
One call

Before, during and after the call

1

Before the ring

The number is matched to the loan, card, paylater or policy record: the amount due, the date, the last conversation and any promise already made. Calling hours for the customer's market and attempt limits are checked before the dial.

2

During the call

The right person is confirmed before any account detail is spoken. The agent states the amount and the date from the record, takes the promise or the instruction, and sends the payment, KYC or renewal link on WhatsApp or SMS while the customer is on the line.

3

When a person is needed

Disputes, hardship and any request for a person go to your team live, with the transcript summary and the promise history on screen. A supervisor can approve an exception on Slack while the caller holds.

4

After hang-up

Outcome tag, transcript and recording are written to the loan, card or policy system. The promise date or callback is scheduled, and a confirmation goes to the customer on WhatsApp or SMS.

Use cases

28 accelerators for financial services

Each agent starts from an accelerator, so a use case is on live calls in about one month.

Cards

Collections and paylater

Onboarding and KYC

Live in one month

Ready in the acceleratorDay 1
  • The call flow and prompts for the use case
  • The fixed opening: right person, who is calling, AI and recording disclosure
  • Outcome tags and the number it is measured by
  • Integrations for telephony, WhatsApp, SMS, CRM and ticketing
  • A test set of calls for the common situations
Done with youWeeks 1 to 4
  • Your numbers and telephony connected in each market
  • APIs to your card, loan, paylater, policy or core system
  • Your approved script, product rules and languages
  • Compliance and information-security sign-off
  • Staging tests on your data, then the first live calls
Live in one month
2 weeks
when your systems are on standard integrations and the script is already approved
1 month
the usual case: one or two system APIs and a compliance review
2 months
when a core system needs a new API or the security review runs long
Compliance

How every call opens

The opening is fixed in the script. It is the same on every call, in every language.

1

Right person

The agent confirms it is speaking to the customer before it mentions any account detail.

2

Who is calling and why

Your organisation's name and the purpose of the call, in the words your compliance team approved.

3

AI assistant, recorded call

The agent says it is an AI assistant and that the call is recorded.

4

The conversation

Only then does the script move to the amount, the date or the KYC review.

Calling window
12 am8 am8 pm12 am

Calling hours

Calls are placed only inside the hours you set for each market, in the customer's local time, for example 8 am to 8 pm for collection calls in Indonesia. Outside them the system does not dial.

Consent for offer calls

Offer calls go only to customers who have consented. In Singapore, numbers are checked against the Do Not Call Registry before a marketing call.

Attempts and audit record

A limit on attempts per customer, and a record of every attempt. Recording, transcript and outcome tag for each call, retrievable by loan, card or policy number.

Personal data

PII is masked in transcripts and logs. Access is by role. The agent never asks for an OTP, PIN, password or full card number. Data handling is set up for each market's law: Singapore's PDPA, Malaysia's PDPA 2010, Indonesia's Personal Data Protection Law (UU PDP, 2022), Thailand's PDPA, the Philippines' Data Privacy Act of 2012 and Vietnam's Personal Data Protection Law of 2025.

Your own cloud project

The agent runs in your Google Cloud project, in the region you choose, for example Jakarta or Singapore. Recordings and customer data stay in your storage.

Transfer to a person

Disputes, hardship cases and any request for a person are transferred live, with the transcript summary.

Engineering

How the agent is built

Speech to speechOne model hears and speaks. The fastest replies, and the caller's tone carries through. The default for live calls.
Caller audioGemini 3.8 LiveAgent audio
CascadedThree models in sequence. Each step can be inspected, and the model cost per minute is lower. Used where the script is strict.
Caller audioChirp 3 speech to textGemini 3.8 FlashGemini 3.8 Flash TTSAgent audio

One turn of a call

CallerAgent Speech detected (VAD)A pause, not the endEnd of turnAgent repliesCaller interruptsAgent stopsAgent answers the new point
Voice activity detection (VAD)Separates the caller's speech from line noise and silence. Only speech is sent to the model, so silence is neither processed nor paid for.
End-of-turn detectionTells a pause in the middle of a sentence from the end of it, so the agent does not reply while the customer is still reading out a number.
Barge-inWhen the caller interrupts, the agent stops speaking at once and the words it did not say are dropped from the conversation.
Answering machine detectionDecided from the audio in the first seconds, before a language model is involved, so voicemail is not counted as a contact.
Noise handlingMotorbike traffic, markets, open offices and speakerphones are common on these calls. The agent stays clear without asking the customer to repeat.
Context compressionA live model re-reads the call so far on every turn. Older turns are summarised, so reply time and cost stay flat on long calls.

Reliability

In-region deployment

The agent runs in the Google Cloud region closest to your customers, for example Jakarta or Singapore. This is fixed before the build, since reply time cannot be tuned afterwards.

Language mirroring

The agent mirrors the customer turn by turn, so it follows the customer's language and not a setting. A call can move from English to Mandarin, or from Malay to English, mid-sentence.

Supervisor and task agents

A supervisor routes to small agents that share the state of the call. The script grows by adding agents.

Supervisor
VerificationPaymentDispute

Model fallback

A health-checked fallback model in the same region takes over mid-call, with the state of the call intact.

Warm transfer

Your team member sees the intent, the transcript summary and the captured details before speaking.

Closing the loop

An analyzer agent keeps each account open until it reaches an end state: paid, promise kept, or handed to your team.

Architecture

Where it sits

Your systemsOwned by you
Loan, card, policy and CRM systemsLoan management system, card system, paylater ledger, core banking, policy administration, Salesforce, Zoho. Two-way sync through APIs.
TelephonyTwilio, Plivo, Telnyx, Exotel, Genesys or SIP trunks, on your existing numbers in each market.
Payments and KYCYour payment links, your auto-debit setup and your own eKYC and KYC review journeys.
Voice layerBuilt and run by Tilicho
Call handlingCall transport, latency control, live call state, prompts and tool calls, PII redaction.
Speech modelsKnows when the caller has finished, hears an interruption, detects a voicemail.
MeasurementResponse time, calls handled without a person, conversions, and what to fix next.
Google CloudModels and compute
ModelsGemini 3.8 Live speech to speech, or speech to text, Gemini 3.8 Flash and text to speech in sequence.
Agent runtimeGemini Enterprise Agent Platform: the runtime and its security boundaries.
Your projectPer-customer isolation, in the region you choose. Recordings and data stay in your storage.
Integrations
TelephonyTwilio, Telnyx, Plivo, Exotel, Genesys, SIP trunks
CRMSalesforce, HubSpot, Zoho CRM, KaptureCX
SchedulingCal.com, Calendly, Google Calendar
TicketingZendesk, Freshdesk, KaptureCX 360, Re:amaze
Messaging and operationsWhatsApp, SMS, web chat, Slack, Gmail, Zapier
E-commerce and customShopify, Google Sheets, MCP Filesystem, custom REST APIs

Anything not on this list, including your loan, card or policy system, is connected through its API during pilot setup. Tilicho builds and maintains it at no extra cost.

The models

Gemini 3.8 LiveSpeech to speech. One model listens, reasons and speaks in real time. This is the model on the call.
Gemini 3.8 FlashReasoning in the cascaded pipeline, and the analysis after each call.
Chirp 3 and Gemini 3.8 Flash TTSSpeech to text and text to speech for the cascaded pipeline.
Gemini Enterprise Agent PlatformThe agent runtime and its security boundaries, inside your own Google Cloud project.
Questions

Common questions

Which languages does the agent speak?

More than 25 languages. In Southeast Asia: Bahasa Indonesia, Malay, English, Mandarin, Tamil, Thai, Vietnamese, Filipino and Taglish. Beyond the region: Hindi, Arabic, Japanese, Korean and Spanish among others. The agent switches language during the call when the customer does.

Can one agent serve several markets?

Yes. Each market has its own numbers, calling hours, languages and approved script, and campaigns are set per market from the same agent.

What happens when the customer wants a person?

The call is transferred live to your team with the transcript summary, so the customer does not repeat the case. You decide which cases always go to a person, such as disputes and hardship.

Where are recordings and customer data kept?

In your own Google Cloud project, in the region you choose, and in your storage. Tilicho runs the agent inside that project.

Do we have to change our telephony or CRM?

No. The agent connects to your existing numbers and systems. There are more than 50 integrations, and other systems are connected through their APIs during setup.

How is the pilot judged?

By the number you choose at the start, for example promises to pay captured or KYC reviews completed, reviewed every week against your current baseline.

See it on one of your use cases

A 30-minute session: a live call with the agent, then a walk through one use case of yours, such as paylater reminders, card activation or a KYC review.

Write to
sharada@tilicho.in