The SENTR platform

AI-powered fraud operations. Built to work your way.

Catch the patterns. Understand the decision. Change the response. SENTR connects configurable rules, machine learning, AI explanations and investigations around your data—not a one-size-fits-all view of risk.

  • Your events. Your risk appetite.
  • Machine intelligence with human control
  • Works beside your current stack

A stronger decision starts with the whole story.

A new device. A reused payment method. A bonus claimed across connected accounts. Each can look ordinary in isolation. SENTR brings the mapped events, history and relationships into the same operation—so your team can investigate the pattern, not just the latest alert.

Connect the systems you already use. Set controls for registration, login, payment, payout, bonus claims and customer-defined events. For qualified evaluations, Shadow Mode lets you compare decisions beside your current stack before changing production.

AI that makes the operation clearer. Not harder to question.

Intelligence should help your team see more and act with confidence. Here is how the intelligence supports the operation today.

Machine-learning foundation

Look beyond the rules you wrote.

Customer-specific anomaly detection learns from clean historical signals to surface unusual activity. Rules remain an independent layer for known patterns and the controls your business needs.

Explore machine learning & feedback →

AI explanations · available today

Read the reason. Inspect the evidence.

Generative AI translates recorded score contributions into plain-language explanations for relevant findings. Analysts can inspect the underlying attribution; the language model does not decide who gets blocked.

See how explanations work →

AI scoring & rule building · available

More intelligence. Less manual tuning.

AI scoring, AI-assisted rule building, the ML pipeline and automatic feature engineering are available. Agree the applicable configuration and approval workflow for your deployment; these capabilities do not imply autonomous publication of live policies.

Explore scoring and the ML pipeline →

Explore the platform

Know what you want to inspect? Go straight to the workbench or capability.

Custom rules & AI rule builder ↗
Author event-scoped logic, inspect contribution and test changes.AI-assisted authoring →
Scoring & the ML pipeline ↗
Inspect scoring paths, customer learning and automatic feature engineering.ML pipeline & features →
Entity intelligence ↗
Five profile families, linked history and Connection Ring.
Reporting & analytics ↗
Standard reports, noisy-rule analysis and SENTR.Citadel custom reporting.
Device signals & integration ↗
Understand mapping, backfill, SDK inputs and the context an API needs.
Governance & evidence ↗
Inspect the controls, attribution and human changes behind the outcome.

SENTR.Citadel or SENTR.Tower

The same platform foundation. Choose who configures the controls and how your team wants to work.

Guided configuration

SENTR.Tower

Start with agreed presets and a simpler review workflow. Keep the engine, explanations and case work; give a named reviewer the evidence to act on exceptions.

Explore SENTR.Tower →Plan a guided start →

Compare the exact capabilities and controls → · Inspect pricing and potential value

SENTR.Citadel begins with discovery and infrastructure planning. Qualified, free 50-day Shadow Mode is an optional proof route. SENTR.Tower starts with fit confirmation and the free 14-day guided start for the initial cohort, with assisted setup and an agreed reviewer workflow.

A useful next step for every question.

Does this fit our business?

Start with the events, exposure and workflow in your industry. You do not need to diagnose the whole stack first.

Explore industry workflows →

Before you decide

The questions worth asking.

What is a fraud operations platform?

A fraud operations platform connects the work around a risk decision: event ingestion, detection, decision policies, explanations, investigations and improvement from outcomes. SENTR combines those stages so an operator can inspect a decision, work the case and change the controls behind future decisions.

Follow the closed loop →
Is SENTR.Tower a different fraud engine from SENTR.Citadel?

No. Both use the SENTR foundation for event scoring, AI and machine learning, explanations, investigations and outcome feedback. SENTR.Tower simplifies configuration through guided presets; SENTR.Citadel gives an experienced operator direct rule, policy and reporting control.

Compare the controls →
Can we evaluate SENTR without replacing our existing controls?

Qualified SENTR.Citadel teams can use a free, optional 50-day Shadow Mode evaluation. SENTR receives the agreed events and compares decisions read-only; your existing stack continues to enforce production decisions. Agree data access, owners and the evidence needed before starting.

Understand the evaluation →

Explore the controls. Picture your operation.

Compare what you can configure yourself and what SENTR can guide. Then bring your use case to a working conversation.

Or see how SENTR works

Your privacy choices

Choose how you use SENTR. Your enquiry, chat and booking do not depend on accepting analytics.

Essential functionality Always active

Delivers and secures the site, remembers this choice and supports the chat or booking you request.

Measures page visits, feature use and enquiry journeys, including recognised campaign sources. Uses analytics cookies. Form answers and chat messages are not sent to Google Analytics.

Advertising trackers are disabled. The same choices apply to UK and EU visitors.

We remember this choice on this browser for up to six months. Changing an active analytics choice reloads the page to stop tracking scripts. Save any unfinished enquiry first.

Website data information