FinTechReview Prompt

Compliance Prompt for EBA Remote Onboarding Signal Checks

This **Luna** review prompt takes your live European onboarding routes and the finalized **EBA guidelines on remote customer onboarding**, then maps each route to the guideline's signal-level verification floor. Luna, the deepidv compliance overseer, returns an EBA control map that rates document-integrity, device-metadata, and biometric-correlation coverage; a signal-check configuration that flags anomalous sub-pixel optical changes and emulated device environments; a latency-impact analysis against your onboarding budget; and a gating spec that says exactly which packages hold before they pass to processing. Built for compliance leads and onboarding engineers at fintechs serving EU customers who need to replace point-in-time document scans with the guideline's dynamic, risk-based checks.

How to use this prompt

1
Open Luna in the deepidv dashboard and paste the full prompt, or run it in Claude, ChatGPT, or Gemini if you are drafting the onboarding design outside the platform.
2
Replace the INPUT section with your European onboarding routes, the checks each stage runs today, your per-stage latency budget, and the EBA guideline sections your firm has already reviewed.
3
Run the prompt and read the EBA control map first: every guideline control is rated covered, partial, or gap with the evidence behind the rating.
4
Hand the signal-check configuration and gating spec to your onboarding engineer, and route the control map to your MLRO; start with any control rated blocking.
5
Re-run the prompt after each onboarding change and after each new EBA, EUDI, or eIDAS 2.0 publication so the design stays aligned before your next supervisory review.

The prompt

Luna, evaluate our European customer onboarding routes against the finalized EBA guidelines on remote customer onboarding, then configure the background verification checks that flag anomalies before any data package passes to our processing streams.

INPUT, the user will paste:
- Active European onboarding routes and the markets they serve, with the verification stages each route touches (document capture, liveness/selfie, device check, sanctions/watchlist screen)
- The checks each stage runs today, including whether document integrity, device metadata, and biometric capture are evaluated and where
- Per-stage latency and throughput budget (soft cap, hard cap, peak onboarding rate)
- The EBA guideline sections the firm has already reviewed
- Any open EUDI wallet or eIDAS 2.0 timelines the firm is tracking

OUTPUT, return the following structured response:

1. EBA CONTROL MAP
For each control the guideline sets (document cryptographic and optical integrity, device-metadata emulator detection, real-time biometric-capture correlation):
- The control (one-sentence summary with the guideline section reference)
- Current coverage (covered, partial, gap)
- Evidence of coverage, or the evidence-absence reason

2. SIGNAL-CHECK CONFIGURATION
- The optical-integrity check placed at document capture (sub-pixel and cryptographic tamper detection) and its pass/hold thresholds
- The device-posture check placed at capture (emulator, virtual camera, and browser-wrapper flags) and its drop rules
- The biometric-correlation check that ties the selfie to a real-time capture log, and the anomaly conditions that route to review

3. LATENCY-IMPACT ANALYSIS
- Per-stage latency delta the proposed checks add, measured against the supplied budget
- Which checks breach a hard cap inline and the asynchronous or pre-computed alternative for each
- Projected throughput at peak under the new flow and the headroom remaining

4. GATING SPEC
- The exact conditions under which a package holds before it passes to processing, by risk tier
- The escalation and manual-review routing when a signal check fails
- The record-keeping schema and cryptographic receipt retained for each onboarding decision for a supervisory inquiry

Be specific and cite the guideline section references where you can. Where the firm's input is insufficient to assess a control or a latency impact, flag the question instead of guessing.

Test it in Claude or another LLM

This prompt is built for the Luna agent inside deepidv, where Luna maps a firm's live European onboarding routes against the finalized EBA remote onboarding guidelines and configures the signal-level checks. You can dry-run the same workflow in any general LLM first with synthetic route and latency data to see the control map before pointing it at real systems.

1
Paste the full prompt into Claude, ChatGPT, or Gemini, but replace the opening 'Luna,' with a role instruction such as 'Act as an EU KYC compliance architect mapping onboarding routes against the finalized EBA remote onboarding guidelines.' Keep the four OUTPUT sections exactly as written.
2
Under the INPUT section, paste the synthetic sample block below so the model has onboarding routes, current checks, and a latency budget to design against.
3
Add one framing line: 'This is synthetic test data. Where a control cannot be assessed from the input, flag it as an open question instead of guessing, and never claim coverage the input does not support.'
4
Check the output shape: an EBA control map with covered/partial/gap calls, a signal-check configuration naming each optical, device, and biometric check per stage, a latency-impact analysis against the supplied budget, and a gating spec. If any section reads vague or invents a control, tighten the role line and re-run.
5
Once the output shape is right, run it live in the deepidv dashboard where Luna executes it against your real onboarding routes and device telemetry.

Synthetic sample data to paste alongside the prompt

Fake test data, safe to share with any LLM. Swap in your own once the output looks right.

EUROPEAN ONBOARDING ROUTES (synthetic, fake):
- Product: retail EUR wallet, markets DE/FR/ES
- Stages: document capture, selfie/liveness, device check, sanctions screen
- Current checks (fake): server-side document OCR only; passive liveness; no device-emulator detection; OFAC/EU consolidated screen at signup
LATENCY BUDGET (fake): document+selfie stage soft cap 4000ms; hard cap 6000ms; peak 400 onboards/hour
EBA SECTIONS REVIEWED (fake): document-integrity ref EBA-TEST-2026-03; device-metadata ref EBA-TEST-2026-05; biometric-correlation ref EBA-TEST-2026-06
OPEN ITEM (fake): EUDI wallet acceptance timeline tracked, fake ref EUDI-TEST-2026-XX

Pairs with on deepidv

Sources & further reading

FAQ

What do the finalized EBA remote onboarding guidelines require?

The EBA guidelines set a single, EU-wide floor for remote customer onboarding: covered institutions must verify a document's cryptographic and optical integrity, evaluate device metadata to catch emulators and virtual camera wrappers, and correlate biometric data against a real-time capture log. Point-in-time scans and administrative data-matching alone no longer satisfy CDD. This prompt maps your routes to those controls and configures the signal checks that satisfy them.

Does this apply to non-EU platforms serving European users?

Yes. Any platform providing digital financial operations to EU customers must align with the guideline's criteria or risk losing processing clearance. Luna evaluates the routes regardless of where the firm is domiciled, and flags the controls where a non-EU stack falls short of the EU floor.

Can I use this prompt outside the deepidv dashboard?

Yes. The structure works in Claude, ChatGPT, or Gemini as a self-assessment framework and will return the control map, signal configuration, and gating spec. Live route pulls, device telemetry, and alert routing to your onboarding team only work when it runs inside the deepidv dashboard.

Run it with live verification data

These prompts work in any LLM. Inside the deepidv dashboard, Luna, Arbiter, and Arc run them against your real sessions, screening lists, and audit trails.

Book a Demo