When a payout partner asks Taptap Send for a recipient's date of birth, an AI agent handles the whole exchange. It finds the sender, emails them for the missing detail and sends the answer back to the partner. No support agent touches the case, so the only wait left is how long the customer takes to reply.
Partner cases that used to take a day or two now close in hours, sometimes minutes. Some of Taptap Send's partners can't keep up.
Jonny Glass, Head of Customer Support Operations (Global) at Taptap Send, walked through the setup with Robbie Tilleard, Lorikeet General Manager for EMEA, on Thursday, November 12.
Partner escalations without a queue
Taptap Send is an app for sending money to family abroad. It relies on payout partners to deliver that money, so when a partner needs more information, the transfer waits.
Tier one agents used to triage every partner ticket to one of two small specialist teams, one for partner escalations and one for requests for information. Volume grew faster than those teams did. Customers waited, whether their transfer was stuck or they'd sent the wrong amount.
Now the agent picks up the partner's request, checks that the transfer ID, name and email match, and looks for the missing detail on the customer's profile. If the detail is missing, it emails the customer and passes the reply to the partner. Faster answers put cases back in partners' queues sooner, which is how some partners fell behind. Jonny called it something “you'd never know or expect.”
“I haven't spoken to anyone else who's doing this,” he said.
The specialists who ran that queue now spend their time on customers who need to talk to a person.
KYC: the provider decides, the agent tells the customer
Taptap Send aims to answer KYC contacts within an hour, because a rejected ID holds up money someone is sending home to family. Often the fix is small, like a date of birth entered one day off.
A third-party KYC provider reviews the ID and sends its decision to Lorikeet as a JSON file. A deterministic tool takes it from there and follows one fixed path. For a clear rejection, the agent tells the customer what didn't match and asks them to try again in the app, so nothing sensitive travels by email. A human agent gets the ticket at the same time and records the decision.
Since customers started getting that email straight away, about 2 to 3% more of them resubmit ID within an hour. Next, the agent will record the decision itself, so the customer can retry the moment the email lands.
Shadow mode first, then 1 in 100
No KYC reply reached a customer until the agent cleared a 95% pass mark.
“We pushed to a pass mark of over ninety five percent in the first phase. The reason that we didn't aim for a hundred percent to be completely honest is our humans are not a hundred percent accurate a hundred percent of the time.” - Jonny Glass, Head of Customer Support Operations (Global), Taptap Send
In shadow mode, every reply the agent would have sent went into an internal note. The KYC team checked all of them and sent the correct ones by hand, which showed the gaps fast. Once the agent passed 95%, one decision in every hundred went straight to the customer. The team checked those too.
Each rollout stage had its own tag, so any error traced back to a version. Jonny could also switch the whole thing off with one button, which gave the compliance team confidence that a problem would stop immediately.
Bring compliance in at the start
Taptap Send brought compliance in just before the AI started replying to customers. Jonny would move that to day one. Taptap Send operates globally, so every regional compliance lead has to be comfortable. Coming in late meant they needed thinking time right at the end.
Next time he'd write the phased plan, share it with compliance before anything goes live and build in the steps they ask for from the beginning. “Taking a bit longer to get to the start line I think is super important.”
What Jonny wants AI on next
Jonny now looks for the most complicated work his team struggles to hire good people for. Once an agent has learned it, it does the job well more of the time. He also wants AI on the proactive support his team never had time to deliver.
Try Lorikeet on your own tickets with a 30-day free trial, or book a demo to see how it handles complex, regulated support.
Try Lorikeet on your own tickets
Start a 30-day free trial. Coach sets up your first concierge in minutes.
Book a call
See what Lorikeet is capable of


