How I Reduced STP Failures 60% on PayNow Corridors While Implementing MAS-Aligned AI Controls

By the Product Scientists

Most teams treat instant-payment speed and AI governance as opposing forces. On a $6B-a-day corridor, I learned they were the same problem — and solving one was the only way to solve the other.

When you run real-time rails — Singapore’s PayNow, India’s UPI, Thailand’s PromptPay — straight-through processing is the entire economic model. A payment that clears untouched costs cents. One that drops out of STP into a manual exception queue costs dollars, hours, and a measurable amount of customer trust. Across the APAC corridor I led at HSBC, that exception tax was quietly eroding $6 billion in daily payment volume.

The reflex is to treat STP failures as a payments-engineering problem: patch the rails, the connectivity, the message formats. My hypothesis was different, and it’s the one that turned out to matter: most STP failures are not payment failures. They are information failures wearing a payments costume.

So before re-architecting anything, I instrumented the corridor and decomposed every exception by root cause.

The breakdown reframed the whole program. The single largest bucket wasn’t the network or rail behaviour — it was screening false positives: legitimate payments halted because a beneficiary name fuzzily matched a sanctions list. The second was structured-data loss in the ISO 20022 / MT translation layer — truncated names, dropped purpose codes, malformed remittance fields. Genuine rail-level faults were the smallest slice.

That meant the highest-leverage intervention wasn’t in the payment rail at all. It was upstream — a pre-flight layer that inspected each message before it entered the corridor, predicted whether it would clear, repaired the structured fields ISO 20022 actually cares about, and ranked screening alerts by genuine risk instead of raw string similarity.

This is where most fintech stories end. It’s also where most regulators start asking questions.

Because in a MAS-supervised environment, you cannot drop an opaque model into the payment path. An AI that “usually” repairs a beneficiary field, or “probably” downgrades a sanctions alert, is not an efficiency — it’s an unbounded liability. The same model that cuts your exception rate can just as easily clear a payment that should have been stopped.

So governance wasn’t a compliance layer bolted on at the end. It was the architecture.

I built every AI decision in the corridor to satisfy four requirements, mapped directly to MAS’s FEAT principles — Fairness, Ethics, Accountability, Transparency:

• Reasoning traces. Every repair and every alert score emitted a structured, human-readable rationale: which field changed, why, and on what evidence. No silent edits.
• Human-in-the-loop thresholds. The model never auto-cleared anything above a defined risk band. It triaged; people decided the cases that mattered.
• Immutable audit trail. Every intervention was logged end-to-end, reproducible and replayable for an examiner — the same traceability discipline I’d later carry into agentic workflows at Thomson Reuters.
• Explainability over accuracy theatre. A slightly less aggressive model I could defend in front of a regulator beat a marginally better one I couldn’t.

The governance layer did something counterintuitive: it made the AI more useful, not less. Because every decision was inspectable, we could safely raise automation thresholds over time instead of capping them out of fear.

The numbers followed the architecture.

On the best-performing corridors, STP failure rates fell by 60%, with the program landing in a 40–60% band across rails. Compliance cost-per-alert dropped from $15.00 to under $0.50 — roughly a 97% reduction — as the screening layer learned to suppress false positives without suppressing real risk. Transparency improved across the full $6B daily flow, which mattered as much to treasury and audit as the cost line did to finance.

But the metric I care about most isn’t on that list. It’s that the control layer stopped being treated as the brake and became the moat. The governance work compliance had initially seen as overhead is exactly what made the automation defensible enough to scale — and exactly what a MAS-aligned market will pay a premium for.

That’s the pattern I keep returning to as a product leader in regulated AI: governance is not the tax you pay for automation. It’s the feature that lets automation compound. Teams that treat trust as friction ship slower and stall at the first regulator conversation. Teams that treat trust as architecture earn the right to move fast — precisely because they can show their work.

On instant rails, the bank that can prove why a payment cleared will always out-scale the one that can only prove that it did.

Amrita Sarkar leads AI, data and payments products across regulated APAC and GCC markets, with 13+ years across HSBC, Thomson Reuters and Deloitte. She writes as The Product Scientist on evidence-driven product thinking at the intersection of fintech, AI governance and trust.