SENTR · FOR IGAMING OPERATORS
Your promotions should reward players, not coordinated abuse. SENTR connects registration, deposit, bonus and payout activity with industry rules, machine learning and AI explanations. Adapt the controls to each campaign and investigate the network behind a suspicious claim.
MECHANISM · ILLUSTRATIVE
SENTR can evaluate bonus_claim with linked accounts, devices and instruments. Shared identifiers are
investigation signals — not automatic proof of a farm.
bonus_claim evaluated with linked-account and instrument context. Innocent sharing
exists; investigation decides.
EVALUATION QUESTIONS · ILLUSTRATIVE, NOT CUSTOMER TESTIMONIALS
HEAD OF FRAUD / RISK DIRECTOR
"Are we stopping bonus abuse—or just adding friction for genuine players?"
Deposit-only scoring leaves the bonus and payout story incomplete. SENTR can evaluate those events with linked identifiers and the context you supply.
CFO / FINANCE DIRECTOR
"The chargeback rate on card payments looks fine until you net it against the players we've blocked."
Separate abuse losses from friction imposed on genuine players. Track reviewed outcomes and the effect of candidate rule changes, rather than assuming every blocked deposit was valuable prevention.
CTO / HEAD OF PLATFORM ENGINEERING
"Our fraud model and our payments provider both need explainability for the regulator. Right now they use different definitions."
A shared decision record gives risk and engineering a common starting point: what the system evaluated, why it responded and what a human changed.
Registration, bonus and payout controls can work from the same player context. See the rules, follow the connections and review the outcome in one platform.
Bonus, account, payout and payment risks share signals. Connect those signals to rules, investigation and outcome feedback rather than handling each event in isolation.
Evaluate bonus_claim events with campaign conditions, velocity rules and linked account context. Industry presets give you a starting point; SENTR.Citadel lets your operator author and test the rule logic as promotions change.
Connection Ring links mapped accounts, devices and payment instruments for investigation. Follow repeated identifiers across events, distinguish direct from inferred relationships and gather evidence before treating a cluster as coordinated abuse.
Bring registration, deposit, bonus and available play context into payout review. Configure decision policies for the event and send uncertain cases to the right reviewer. This is fraud decisioning; it does not replace AML or sanctions screening.
Keep event attribution, reviewer actions and relevant case evidence together for the dispute process you already run. Automated chargeback filing and settlement remain roadmap, not an inclusion in current SENTR.
A use-case walkthrough on SENTR’s six-stage loop: Ingest, Detect, Decide, Explain, Investigate and Improve. See how the loop works →
Slide to explore the operating sequence
Use-case sequence
Onboarding and funding events mapped into SENTR with the identifiers you already hold.
Use-case sequence
bonus_claim evaluated with linked accounts, devices and instruments — signals for review, not automatic guilt.
Use-case sequence
Behaviour and withdrawal context stay connected so policy can differ by event without losing the trail.
Platform loop
Plain-English rationales and linked cases on the same foundation as detection.
Platform loop
Recorded outcomes feed lists and controls. AML/sanctions screening remains roadmap — not sold as current.
Use-case sequence
Onboarding and funding events mapped into SENTR with the identifiers you already hold.
Use-case sequence
bonus_claim evaluated with linked accounts, devices and instruments — signals for review, not automatic guilt.
Use-case sequence
Behaviour and withdrawal context stay connected so policy can differ by event without losing the trail.
Platform loop
Plain-English rationales and linked cases on the same foundation as detection.
Platform loop
Recorded outcomes feed lists and controls. AML/sanctions screening remains roadmap — not sold as current.
When licensing or governance asks how an automated fraud decision was made, “the model is proprietary” is not an operating answer. SENTR stores a human-readable rationale for fraud decisions you configure — evidence for deployer assessment. AML and sanctions screening remain roadmap and are not sold as current product.
LICENSING RISK
iGaming licences — MGA, UKGC, GCB — often require operators to demonstrate control over automated decision-making in fraud and player-protection workflows. Decision classification under the EU AI Act depends on the specific system and use; fraud detection is not automatically “high-risk” merely because it is automated. SENTR helps you keep a readable decision trail for deployer assessment. This is education, not legal advice, and not a licensing survival guarantee.
MGAUKGCGCB
SENTR supports decision evidence for your legal and compliance review. It does not certify your licensing compliance or replace your AML programme.
Read the decision-evidence notes →Automated dispute filing, AML and sanctions screening remain roadmap. Applicable legal obligations must be assessed for your deployment.
Put SENTR beside your current controls for a qualified, free 50-day read-only evaluation. Compare decisions, investigate differences and separate confirmed findings from modelled impact. Your data. Your decision.
Connect · agreed scope
We map the agreed event types, identifiers and available history with your technical contact. Your existing system keeps making production decisions. Integration scope and readiness determine the start date.
Evaluate (Days 1–50)
SENTR scores the agreed feed without enforcing its decisions in production. Compare outcomes, investigate disagreements and record confirmed findings separately from open questions.
Decide (Day 50)
Review a Day 50 report covering decision comparisons, investigated findings, operational measurements and modelled financial impact. Some fraud and chargeback outcomes need longer to mature. Decide together whether to proceed, refine the evaluation or stop.
Shadow mode is qualified and read-only while evaluation runs. No production commitment required to evaluate. Shadow Mode is optional.
How Shadow Mode works → Book an Architecture Session →
FOR YOUR ENGINEERING TEAM
Use supported REST APIs, webhooks and other mapped ingestion paths. Scoped credentials and a provisioned sandbox support integration testing. Automated Adyen/Stripe mapping is still in development.
Agree the event map, history requirements, test cases and production boundary before implementation. Explore data & integrations →
SENTR uses AWS regions in Ireland and Germany. Confirm data flows, explanation-processing subprocessors and residency terms in the security review and DPA. Read security & data →
Keep your payment infrastructure while evaluating SENTR. Agree data export, retention and exit arrangements before production; we do not assume a change of processor is required.
Inside the workflow · illustrative configurations
Bonus abuse is not just payment fraud with a different label. Registration, claims, deposits and withdrawals each need their own controls and a connected player history.
Connect registration, bonus_claim, deposit and relevant activity history. Supply the promotion conditions and stable player, device and instrument identifiers needed by the rule.
Start with bonus-abuse rules and presets. In SENTR.Citadel, author AND/OR conditions, test against available history and use Monitor before changing live scores. Give the claim its own review/block policy.
Open the Connection Ring, inspect related players and distinguish coordinated abuse from households or shared infrastructure. Record the reason so bonus loss is not confused with stolen-card fraud.
Carry login, deposit, bonus and available play context into the withdrawal. A familiar player or successful deposit does not settle the later risk decision.
Use withdrawal-scoped rules, profiles and decision policy. An action policy can create a case and notification; the operator’s connected system enforces any hold or release.
Give the reviewer a checklist, linked activity and the score breakdown. Record an override with a written reason and use case outcomes and rule analytics to assess friction as well as confirmed abuse.
See the controls behind these workflows: SENTR.Citadel product deep dive → Compare guided SENTR.Tower →
Your industry shapes the rules. Both models share customer-specific machine learning and AI explanations. Choose how much configuration your team wants to own.
THE SHIFT
Bonus campaigns should attract customers—not turn your fraud team into a spreadsheet operation. SENTR brings event-scoped rules, customer-specific anomaly detection and connected casework into one workflow. Set the appetite, inspect the reason and improve the next decision. Let us map that to your player journey.
Book your Architecture Session →A working session, not a pitch deck. Optional Shadow Mode is free for qualified SENTR.Citadel evaluations; production is a separate decision.