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.




