Application fraud
One identity, many merchants
Stolen or synthetic identities get tried at several merchants in the same hour. A single merchant's view misses the pattern.
Threat squad
Bella Nova — Senior AI BNPL Risk Strategist
BNPL risk scoring your credit team can explain
Bella Nova — Senior AI BNPL Risk StrategistBella Nova is an AI agent that scores buy now, pay later applications for fraud and credit risk at checkout, tracks each merchant's exposure against the limits you set and watches the book for early default signals. She recommends and explains. Your credit policy and your risk team set what happens next.
Bella Nova
Checkout application #33508 scored
IllustrativeHeld for review
Fraud 0.72 · credit risk medium
Flag explained
“New device, delivery address differs from billing, three applications across merchants today.”
Job description
What Bella Nova does Job description
Bella Nova is a Senior AI BNPL Risk Strategist. She sits beside your checkout decision flow and your loan book, scores what comes through and prepares the evidence your lending risk team reviews.
AI AGENT · THREAT SQUAD
BELLA NOVA
Senior AI BNPL Risk Strategist
REPORTS TO
Your Head of Lending Risk
WORKS WITH
Your checkout decision engine, merchant platform, loan servicing and collections systems
DEPLOYED
Shadow mode first, then the autonomy you set
KEY RESPONSIBILITIES
01Score BNPL applications at checkout for fraud signals and credit risk, with the reasons behind each score
02Recommend approve, refer or decline against your credit policy, for your decision rules to apply
03Track each merchant's exposure against the limits you set and flag breaches to your risk team
04Watch the book for early default signals and send at-risk accounts to your collections or care team
05Send held and referred applications to an analyst with the evidence attached
AUTONOMY MODEL
LOWMEDIUMHIGH
Low risk
Low-risk applications follow your credit policy path, if you allow it
Medium risk
Held for an analyst by default
High risk
Always goes to an analyst
You set the threshold per rule.
Kill switch: Turn Bella off at any time
Options
How the options compare
| CRITERIA | Bureau score plus rules | Manual credit review | Bella Nova |
|---|---|---|---|
| Time to first results | Rule build and tuning | A hiring and training cycle | Shadow mode on your live applications |
| Who decides | Rule thresholds | Credit analyst | Your credit policy and analysts, inside bands you set |
| Fraud across merchants | Limited to the data in the rule | Rarely visible at checkout speed | Linked across merchants and applications |
| Why an application was held | Rule ID | Analyst notes | Plain-English reason with the signals behind it |
| Book monitoring | Scheduled reports | Periodic portfolio review | Merchant exposure and early default signals watched continuously |
| Where it's weaker | Thin-file customers score poorly | Can't keep up at checkout volume | Credit scoring is high-risk under the EU AI Act, so you carry its documentation and oversight duties |
Works best with
AI agents that work best with Bella Nova
Bella's scores get sharper when other agents add what she can't see at checkout.
THREAT
Lena Credit
Senior AI Underwriting Security Director
Checks income and documents on larger or longer-term credit lines.
Meet LenaTHREAT
Aiden Flux
Senior AI Fraud Risk Analyst
Scores the repayment transactions on the book for fraud and mule activity.
Meet AidenTRUST AND IDENTITY
Iris Verma
Senior AI Identity Verification Specialist
Verifies documents and liveness when an application needs a stronger identity check.
Meet Iris
Thoughts that matter
Insights on AI agents, financial crime and compliance
What we're learning about AML, fraud and the evidence examiners ask for.
Best AML Software in 2026: An Honest Comparison for Banks and Fintechs
Read More
goAML Registration and STR Filing in the UAE: A Step-by-Step Guide for Reporting Entities
Read More
Transaction Monitoring Software: UAE Acceptance Checklist
Read More
PEP and Sanctions Screening: What the MLRO Owns
Read More
Session Risk Scoring: Continuous Authentication for Banks
Read More
Impossible Travel Detection in Banking: How It Works
Read More
Questions? We Have Answers
-1.svg)
Frequently Asked Questions
Still have questions?
Talk to the people who build the agents. We'll answer per capability, yes or no.
An AI agent scores each application for fraud and credit risk at checkout, links repeat attempts across merchants and watches the book for early default signals. Bella Nova explains every score in plain English and routes applications by the credit policy and autonomy bands your team sets.
She recommends. Your credit policy and decision rules act on that recommendation, and you choose which risk bands run automatically. Medium risk is held for an analyst by default and high risk always is. A kill switch turns Bella off without touching your checkout.
AI used to evaluate the creditworthiness of individuals is listed as high-risk in Annex III, and fraud detection is carved out. Bella keeps fraud and credit scores separate, with their own explanations, so your documentation can treat them separately.
Yes. Under GDPR Article 22 and similar laws, customers have rights around automated decisions. Every Bella score carries the signals behind it, so your team can give a specific answer.
Application data from checkout, merchant details, device and IP data, and repayment history from your book. Past outcomes on fraud and arrears help her learn what your team treats as risk.
Bella scores your live applications and book, but nothing changes at checkout. You compare her scores with your current engine and with real outcomes. You decide whether, and where, to switch on any autonomy afterwards.
FluxForce runs as SaaS, on-premise or hybrid, built on Microsoft Azure. We agree data residency and which components run inside your environment during deployment design, before any data moves.