Laava LogoLaava

Project context

AI-Assisted KYC Screening

KYC screening workflow that checks clients against sanction lists and public sources, then produces structured risk profiles analysts can review instead of building every dossier from scratch.

Validated conceptFinancial crime and onboarding team2025

Client identity kept confidential

Macro of a metal bank-vault dial and lock — financial-grade screening
3h → 45min
Dossier prep time
Measured
100%
Known risks found
Measured
25
Test dossiers
Observed

Evidence

Measured on 25 test dossiers against known risk signals. The workflow supports analyst preparation and does not automate final KYC decisions.

The challenge

The solution

Technology stack

LangGraphAzure OpenAIQdrantPython

The result

The workflow reduced dossier preparation time from roughly 3 hours to 45 minutes per client while keeping traceability back to the underlying sources. That is a material operational gain in onboarding and periodic review work, where analyst time disappears quickly into repetitive preparation.

The point is not to remove human judgment from KYC. It is to move analysts faster toward the part that actually requires judgment.

Next step

Want to explore where this could land first in your operation?

Start with one concrete process. In the AI Opportunity Scan we assess where AI adds value and what the best first route looks like.

AI-Assisted KYC Screening Case Study | Laava