AI-native decisioning engine

Your customer may not be human.

Nyx, our decisioning engine, makes your business readable to AI agents, then decides on them when they buy, with the reason attached.

POST /api/interface/decision/decide
// card_not_present · SAR 2,914.00 · new device
// response · 87ms
{
  "action": "review",
  "score": 0.91,
  "severity_band": "high",
  "reason": "velocity + geo mismatch",
  "evaluators": [
    {"rule": "cnp_velocity", "hit": true},
    {"model": "txnCBM@v14", "score": 0.91}
  ],
  "audit_ref": "dec_EXAMPLE…",
  "latency_ms": 87
}
REPRESENTATIVE RESPONSE · SAMPLE DATA · LATENCY TARGET <100MS†
Veterans of JPMorgan · TSYS · Pine Labs Managed by us, your cloud, or your data center Be found by your customer's agent · pilot now
Why now

Three forces are compressing the decision window at once.

Attacks are produced faster than models retrain, liability for the decision is landing on you, and a new kind of customer has started transacting on its own. Fraud is where most decision stacks break first, but none of these three stops at fraud.

Force 1 · the attack

The attack is automated.

Deepfake KYC, synthetic identity and GenAI social engineering, generated at a scale supervised models cannot retrain against.

42.5%
OF FRAUD ATTEMPTS NOW AI-DRIVEN · SIGNICAT · 2024
Force 2 · the liability

The liability is moving to you.

Regulators are shifting responsibility for real-time controls, reporting and reimbursement onto the party making the decision, on staggered timelines.

2028
EU PSD3/PSR LIABILITY SHIFT · UK APP REIMBURSEMENT ALREADY IN FORCE 7 OCT 2024
Force 3 · the customer

The customer may not be human.

Agents find, evaluate and buy on a person's behalf, and the device and behavioral signals every stack leans on vanish with them.

$1.5T
AGENTIC COMMERCE BY 2030 · JUNIPER · 2025

Force 2, by regime  ·  EU · VERIFICATION OF PAYEE (IPR), PSD3/PSR LIABILITY SHIFT 2028  ·  UK · APP REIMBURSEMENT IN FORCE 7 OCT 2024  ·  US · NO FEDERAL MANDATE YET, LIABILITY PRESSURE BUILDING  ·  SG · MAS SHARED RESPONSIBILITY FRAMEWORK  ·  IN · RBI MASTER DIRECTIONS IN FORCE JULY 2024  ·  AU · SCAMS PREVENTION ACT 2025  ·  SA · SAMA CFF IN FORCE 13 APR 2026  ·  AE · CBUAE 3057, FINES SINCE 31 MAR 2026

The decision domains

One engine. Six decisions. An honest status on each.

Nothing domain-specific is welded into the kernel. A versioned pack declares the entities, features, policies and actions a domain needs, so the second decision is a configuration exercise rather than a second procurement.

Five of these are decisions a bank, fintech, processor or lender makes about a customer. Agentic commerce is the one a merchant runs, to be found by the agents now shopping on a customer's behalf.

Two are ready to pilot today: fraud on the institution side, agentic commerce on the merchant side. Any of these can be the one we start with. Compare all six →

The engine

The verdict stays fast. The investigation runs beside it.

One synchronous call returns the action, score, reason, rule hits, model version and audit reference. The heavier AI work runs asynchronously and never enters the authorization path.

Nyx · ONE SURFACE, END TO END
INGEST
file·api·kafka·db
CANONICALIZE
contracts·pii·dlq
FEATURES
online + offline
TRAIN
registry·versioned
POLICY
authored·simulated
DECIDE
<100ms target†·explained
SYNC API
one POST call
AI INTELLIGENCE: case summaries · daily briefs · policy authoring · investigation, governed in one place

† Design target to validate in the first pilot, not yet independently benchmarked. Architecture, primitives and the decision API →

Deployment & trust

How it deploys is your call, not our constraint.

The same engine, the same API and the same audit trail in all three models. Pick the one your regulator, your security team and your stage of growth allow.

Hosted by us · managed

We run it in the region you pick, single-tenant by default. Multi-tenant where one institution serves its own merchants on it. The fastest route for fintechs, processors, merchants and smaller institutions with no platform team to spare.

Your cloud

Deployed into your own AWS, Azure or GCP account and VPC. Your keys, your network, your data residency; we ship and support the release.

Your data center

On-premises inside your perimeter, for institutions whose regulator or policy requires it. No bulk extraction to a third-party black box.

DATA HANDLING

Your data stays yours in every model. Native data-lake integration, PII masking, injection guardrails on every AI call, and models trained on your transactions only.

ACCESS & AUDIT

Role-based access and enterprise SSO (Keycloak / OIDC). Full audit trail and idempotent decisions, structured for regulatory reporting.

COMPLIANCE MAPPING

SAMA CFF and CBUAE 3057 control mappings are written. Mappings for other regimes are produced with the first partner in that jurisdiction.

PORTABILITY

Open standards end to end. Your models, features and decision history stay portable, and exit terms are written into the pilot, not discovered later.

Full architecture, governance and operating posture on the Platform page →

Who's building this

A team that has built the systems businesses decide with.

THE TEAM

NaxVerse is a senior engineering team spanning real-time authorization, fraud scoring, risk decisioning, ML infrastructure and DevSecOps. People who have built and operated these systems inside banks and payment processors, now building the platform they wished they had.

Led by founder Umesh Kolhe: two decades across the payments lifecycle at JPMorgan, TSYS and Pine Labs, from authorization and fraud scoring to the ML infrastructure behind them.

JPMorganTSYSPine LabsisPAY
THE COMPANY

NaxVerse Technologies Pvt Ltd is headquartered in Noida, India, in the Delhi NCR, and works with banks, fintechs, processors, lenders and merchants wherever they are regulated. Founder-led, pre-launch, and forming a small design-partner cohort now.

Press & due-diligence pack →

Advisory group forming across fintech, payments and risk

Pick a decision · prove it on your data

Run a pilot on your data.

Prove one decision domain against your real data, in the deployment model you want. Then extend the same governed engine into the next one.

Not a bank, or not the fraud use case? Fintechs, processors, lenders and merchants run on the same engine, and so does the decision you need. Write to us.

HELLO@NAXVERSE.AI · FOUNDER-LED, PROCUREMENT-READY · DUE-DILIGENCE PACK ON REQUEST