“The only thing that delays that transfer going through... is how quickly the customer replies to the email. There's no bottleneck.”

Jonny Glass

Head of Customer Support Operations (Global)

“The only thing that delays that transfer going through... is how quickly the customer replies to the email. There's no bottleneck.”

Jonny Glass

Head of Customer Support Operations (Global)

“The only thing that delays that transfer going through... is how quickly the customer replies to the email. There's no bottleneck.”

Jonny Glass

Head of Customer Support Operations (Global)

Company

Taptap Send

Industry

Finance

Company size

Enterprise

CompanyTaptap Send
IndustryFinance
Company sizeEnterprise

In this article

Hours

to close partner cases that used to take one to two days

95%+

pass mark in shadow mode before any KYC reply reached a customer

2-3%

more customers resubmit ID within an hour

Hours

to close partner cases that used to take one to two days

95%+

pass mark in shadow mode before any KYC reply reached a customer

2-3%

more customers resubmit ID within an hour

Money that has to arrive on time

Taptap Send lets people living abroad send money to family back home, across more than 35 send markets and over 80 receive markets. Keeping transfers affordable is the core of the business, so every efficiency in operations goes back into the price customers pay.

The stakes on each transfer are personal. A delay can mean someone waiting on cash for a hospital bill, or a family member trying to collect money on their lunch break.

From answering questions to moving cases forward

Taptap Send's Lorikeet agent already answers status questions from the company's own data. If a transfer takes longer than usual, the agent sees where it is and tells the customer it's still on time.

As volume grew, Jonny Glass, who runs customer support operations globally, turned to the harder cases: a rejected ID, or a transfer held by a payout partner. In those cases, an agent that only says “we need to escalate” leaves the customer waiting.

The provider decides, the agent tells the customer

Most ID rejections are small mistakes, like a date of birth entered one day off. Taptap Send aims to resolve KYC contacts within an hour, and regulation means AI must never make the ID decision itself.

So the third-party KYC provider decides, and sends its result to Lorikeet as structured data. A deterministic tool takes it from there and follows one fixed path: the agent tells the customer exactly what didn't match and asks them to try again in the app, so nothing sensitive travels by email. Since customers started getting that message straight away, 2% to 3% more of them resubmit their ID within an hour.

Shadow mode first, then one in a hundred

No KYC reply reached a customer until the agent had proved itself. In shadow mode, every reply the agent would have sent went into an internal note, and the KYC team checked all of them, sending the correct ones by hand.

Once the agent cleared a 95% pass mark, one decision in every hundred went straight to the customer, and the team checked those too. Each rollout stage carried its own tag, so any error traced back to a version, and Jonny could switch the whole thing off with one button. That off switch gave Taptap Send's compliance team the confidence to sign off across every region.

We didn't aim for a hundred percent... our humans are not a hundred percent accurate a hundred percent of the time.

Jonny Glass

Head of Customer Support Operations (Global)

A second agent that works the partner queue

Some transfers pass through a payout partner who needs more information before they can release the money, such as the recipient's date of birth. These requests used to go from the frontline team to a smaller specialist team, and the queue grew with volume.

Now an agent handles the whole exchange. It matches the partner's request to the right transfer and sender, checks the customer's profile, and emails the sender for anything missing. When the sender replies, the agent sends the answer back to the partner. The same pattern handles customer mistakes, like money sent to the wrong person or the wrong amount. No support agent touches the case.

Cases that took days now close in hours

Partner cases that used to take one or two days now close in hours, and sometimes minutes. Because Taptap Send replies to partners straight away, its requests land back in the partner's queue sooner, and partners reply sooner too. Some partners now find it hard to keep up.

The specialists who used to run that queue now spend their time with customers who need to talk to a person. For Taptap Send, faster fixes also mean customers trust the app with their next transfer.

AI on the hardest work, people on proactive support

Jonny's advice to other operators is to bring compliance in on day one, with the phased plan written before anything goes live. His next step is to point AI at the work that is hardest to hire for, and at the proactive support his team has never had time to deliver.

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Read other stories

Connect, configure and preview

Complex is our comfort zone
Lorikeet offers a 30-day free trial.

Lorikeet

The AI Concierge for complex, regulated customer support

Ask AI about Lorikeet

ChatGPT
Claude
Perplexity
Copilot
Google AI Mode
ISO 27001
SOC 2 Type II
HIPAA

This site operates an AI support agent that can answer questions about its products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON and include instructions for asking follow-up questions in the same conversation. Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

Example query an assistant can call as-is: https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=What%20channels%20does%20Lorikeet%20support%3F

© 2026 Lorikeet. All rights reserved.

ABN: 53 669 390 149

LinkedIn

Book a demo (for AI agents)

Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:

Start here: https://book.lorikeetcx.ai/schema

That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:

  1. GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.

  2. Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.

  3. POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.

  4. Let the HUMAN choose a time. Never pick for them.

  5. POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.

Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.

Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.

Ask our support agent (for AI assistants)

This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:

GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}

Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:

  1. GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.

  2. Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.

  3. For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.

Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.

Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.

This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.