A payment status call with a pending next step
Hear how the agent understands context, connects to approved systems and leaves a clear next step.
Finance, digital payments
92.6% of calls answered instantly, no exceptions
Over a 30-day window, an inbound support agent and an outbound survey pilot handled 479 interactions for a digital payments platform, with the large majority of calls picked up the instant they came in.
Dring AI workflow demo
A payment status call with a pending next step
A calm support exchange that checks the payment, explains what is known and records a follow-up without presenting a pending case as resolved.
479interactions in 30 days (417 support, 62 survey)
92.6%of inbound calls answered instantly
70.3%of dialogues reached a conclusion
96.9%positive sentiment
Context
When the call is about money
A digital payments platform handles transaction status, failed-payment and account questions by phone, the kind of call where every minute on hold reads as a warning sign.
Support volume was growing and issues were time-sensitive: a pending transfer or a failed payment needed an answer now, not after a queue. The platform also wanted a reliable way to measure satisfaction after a support interaction, rather than relying on occasional manual outreach.
The agent
Live support, plus a survey pilot
The inbound support agent reads the account and transaction state, resolves what it can on the call, and hands off to a human agent with full context when a case needs judgment or a manual bank trace.
A separate outbound agent runs a satisfaction survey pilot after support interactions, scoring how likely a customer is to recommend the platform.
Hi, a transfer I made yesterday still shows pending.
I can see it, it's sitting with the receiving bank right now, that typically clears within 24 hours. I'll text you the moment it settles.
Okay, and if it doesn't clear by tomorrow?
Then I'll open a trace with the bank directly, no action needed from you, just reply to that text if it's still pending after 24 hours.
OutcomeResolved by AI
SentimentPositive
How it was delivered
Built for a time-sensitive line
- Discover
Map top call types
Pending transfers, failed payments and account questions were identified as the highest-volume, highest-urgency reasons for calling.
- Build
Wire into account systems
The agent was built against live transaction and account state, not a cached snapshot.
- Test
Simulate disputes
Failed-transaction and disputed-charge scenarios were run as simulated conversations before launch.
- Launch
Live on the support line
The inbound agent went live answering the main support line, with human handover always available.
- Evolve
Pilot the survey
An outbound satisfaction survey was run as a pilot on a smaller group before any decision to scale it.
Results
What the 30-day window shows
| Metric | Result | Note |
|---|---|---|
| Interactions (30-day window) | 479 | 417 support, 62 survey |
| Calls answered instantly | 92.6% | No queue |
| Dialogues reaching a conclusion | 70.3% | 40 resolved by AI alone, 218 handed to a human cleanly with context |
| Sentiment | 96.9% positive | |
| Survey pilot recommend score | +54 | Average 8.4/10, n=13, small sample |
What we learned
Speed is the product
In payments, instant pickup carries more weight than in most other lines. 92.6% answered instantly is the number that builds trust before the agent says a word about the actual issue.
Resolution rate alone undersells the result here. Of the 70.3% of dialogues that reached a conclusion, most were handed to a human, and the value was in how cleanly: 218 handoffs carried full context, so the customer never repeated themselves.
The survey pilot's +54 recommend score is encouraging, but n=13 is too small to call it a trend. The next step is running it at a larger sample before drawing any conclusion from it.
Put an agent on your support line
See how it would handle your busiest payment questions.