Deterministic contribution
Which rules, lists and score components fired—stored with the decision so operators can reproduce what happened.
Capability · Explain
A score raises the question. Show your team the answer.
Read an AI explanation of the relevant findings, then inspect the rules, signals and score contributions behind it. SENTR connects that evidence to the case and any human override—so analysts, risk leaders and reviewers can work from the same facts.
- Contribution stored with the decision
- Overrides keep a written reason
- Original decision and human action kept distinct
Why “we have logs” is not enough
Scattered logs force analysts to reconstruct why a payment was blocked three systems later. Governance and commercial stakeholders need attribution that travels with the decision—and a clear line between what the system computed and what a human changed.
Read the diagram
A sample payment event has score 72 and a review response under auth.default. Selected contributions are device velocity +18, first-seen IP +12 and payment-method reuse +8. They show part of the attribution, not a sum to 72. Recorded findings are the evidence; an AI explanation makes them readable.
Readable on the surface. Inspectable underneath.
See what the system calculated, how AI explained it and what a person changed.
What explanation does — and does not — do
AI explanations
Natural-language explanations render relevant rule and anomaly findings. Every event retains attribution; quiet events need not generate a prose narrative. The language model explains, never decides.
Human decisions, attributed
A written override reason records what changed, who changed it and when—alongside the original system decision.
What this looks like in practice
Blocked withdrawal with an override
A withdrawal is blocked on rule contribution plus policy threshold. The on-call reviewer overrides to allow after confirming a known travel pattern, with a written reason.
- Withdrawal event
- Rule + policy block
- Travel pattern confirmed
- Override to allow
Nobody has to invent the story after the fact—the decision already carries both machine and human authorship.
Traceable decision evidence
Explainability and audit exports help your team inspect and document decisions. They support your assessment; they do not automatically establish regulatory compliance for your deployment.
Machine learning & AI
Learn your patterns. Make the findings understandable.
Authored rules cover patterns your team knows to look for. Unusual behaviour can still deserve attention when no existing rule describes it.
SENTR’s customer-specific anomaly model learns normal activity from clean signals, independently of authored rule outputs. It returns a separate risk score and contributing signals. Training runs overnight once sufficient suitable data is available; evaluation and training are different processes.
SENTR Product viewDemo data
Enlarge view The matched rule, its impact and the recorded reason—together on the event.
The explanation has something concrete behind it: the matched check and its contribution.
Go deeper: Machine learning & AI
- Inspect both scoring paths
- Rule contributions and AI score breakdowns remain distinct. Analysts can inspect severity, exact score impact, confidence and the reasons that contributed most.
- Read the explanation, then verify it
- Generative AI translates relevant recorded findings into natural language. Attribution is stored for every evaluated event; quiet events need not generate a prose narrative. The language model explains the score, not the block decision.
- Keep feedback accountable
- Validated outcomes and corroborating signals inform the customer-model learning process. A reviewer’s override is not blindly accepted as training truth. Sector and global model tiers are available where agreed for your deployment.
Give analysts readable reasons without hiding the evidence behind them. AI scoring, the AI rule builder, the ML pipeline and automatic feature engineering extend this foundation. Agree their configuration and access for your deployment.
Stop defending a score. Start explaining the decision.
Explore the evidence trail, then show us a decision your team needs to explain more clearly.