SENTR · SHADOW MODE

How shadow mode actually works

One of us has something to lose. It's not you.

For 50 days, SENTR runs alongside your existing stack — read-only, silent, parallel. You get a full intelligence report. We get the chance to earn your confidence. No commitment changes that math.

Read-only connection. No risk. No cutover.

From first call to live intelligence

Three steps. No commitment until you've seen the data.

Live architecture map

SENTR Architecture Session — mapping your risk stack.

Step 1

First contact & Architecture Session

Deep dive into your way of working.

We map your current fraud stack and risk architecture. No pitch deck — a working session. We define the metrics we'll improve, confirm you're a fit for shadow mode, and build your 50-day roadmap before we connect a single line of code.

  • Map your current fraud stack and risk architecture
  • Define success metrics and detection benchmarks
  • Build your personalised 50-day shadow mode roadmap
  • Confirm integration requirements with your technical lead
  • No commitment at this stage — walk away if it's not a fit

The read-only connection

No data migration

Your transaction data stays in your systems. We connect via read-only API to your transaction event stream. Nothing in your production environment changes.

8-day integration

Our dedicated integration engineer manages the full setup. Your team provides API access and a technical contact. Typical timeline: 8 business days from kickoff to live.

Zero production risk

We observe only. We write nothing to your production environment. Your fraud platform keeps making every live decision throughout.

The 50-day parallel run

  1. Day 0 — Integration live.

    SENTR connected to your transaction stream. Your existing platform unchanged. Nothing in your live environment is touched.

  2. Days 1–49 — SENTR runs. You watch.

    SENTR processes every transaction you process. Applies our detection logic. Writes zero decisions to your production system. Your analysts see nothing different in their daily queue. Optional: weekly intelligence reports available on request.

  3. Day 50 — The data is yours.

    Full intelligence report delivered. Your fraud data, analyzed. Side-by-side comparison with your current platform's output. Then you decide.

  • Fraud your platform caught — confirmed
  • Fraud your platform missed — revealed
  • False positives you'd remove
  • Chargeback impact delta
  • EU AI Act explainability per decision

What the Day 50 debrief covers

  1. Side-by-side detection comparison

    We show you every transaction SENTR flagged that your current platform passed (missed fraud) and every transaction SENTR would have cleared that your platform flagged (false positives). You see the delta on your own data.

  2. Chargeback attribution analysis

    For any chargebacks that landed during the 50-day window, we map them back to the detection decision at transaction time. You see how often your current model was right, wrong, and why.

  3. Investigation effort audit

    We show you where your ops team spent manual review hours during the period, and where SENTR's explainability layer would have reduced that queue. We put a number on it.

  4. EU AI Act readiness snapshot

    Based on the 50-day run, we show which of your model's decisions would satisfy Article 13 explainability requirements and which would not. Not a compliance opinion — a technical readout.

  5. Go/no-go framing

    We state our view directly: whether the data supports going live with SENTR, and on what timeline. If the data doesn't make the case, we say so. The report is yours either way.

The Day 50 intelligence report

Exactly what you receive.

Fraud matched

Transactions we flagged as fraud that your platform also caught. Validates alignment.

Fraud missed

Fraud we detected that your platform let through. This is the impact gap.

False positives removed

Legitimate transactions you blocked that we would have approved. Recovered revenue.

Chargeback delta

Estimated chargebacks we would prevent. € impact projection for Year 1.

EU AI Act explainability

Per-decision reasoning log. Audit trail compliant with August 2026 enforcement.

This report is the data you use to make the switch — or walk away. No invoice either way.

Integration architecture

We connect to where your fraud decisions are made — not to your payment processor.

SENTR integrates via read-only API to your internal transaction event stream and chargeback data layer. We do not sit between you and your acquiring bank. We do not connect via a payment processor's API. We connect directly to your risk infrastructure — wherever fraud decisions are made.

Where decisions are made

Transaction event stream

We connect via read-only API to your live transaction data — your processing core, your event log, or your internal reporting layer. Your stack doesn't change.

Running alongside your current tool

Fraud & risk engine output

SENTR observes your existing fraud decisions and runs its own logic in parallel. At Day 50, you see both outputs side by side. No replacement required before you decide.

Full-loop visibility

Chargeback data layer

We ingest your dispute and chargeback data to map the full fraud-to-resolution picture. Shadow mode shows you both the fraud your platform caught and the losses it didn't.

Questions about integration for your specific stack? Contact our integration team — hello@sentr.io

EU AI Act compliance output

Building your audit trail in shadow mode.

Sample explainability output

TXN-88421
DECLINE Model confidence 94.2%
Evaluation mode
Shadow · read-only
Risk signals
Velocity · Geo mismatch · CNP · MCC risk

Rationale (human-readable)

  1. Velocity anomaly: three successful authorisations from the same device fingerprint within four minutes — exceeds your configured burst threshold for this segment.
  2. Billing country (DE) inconsistent with IP geolocation (high-risk jurisdiction).
  3. Card-not-present with elevated merchant category risk score.
EU AI Act export pack · ready in < 45 min

Human-readable explainability log

SENTR generates a full explainability log for every fraud decision — human-readable, regulator-ready, exportable in under 45 minutes. Shadow mode builds that baseline during the proof period. You do not need to be live on SENTR before August. You need to be able to demonstrate you are building toward compliance. Shadow mode starts that clock.

  • Per-decision explainability — why we approved or declined
  • Exportable in under 45 minutes to compliance-ready format
  • Builds your audit trail baseline before August 2026 enforcement
  • Regulator-ready — no post-hoc remediation required

Ready to see it on your data?

Book a 20-minute Architecture Session. We map your current risk setup and walk you through what shadow mode would find for your transaction volume.

Book your Architecture Session →

No pitch deck. No contract. No follow-up sequence unless you ask for one.