PEP Screening
As part of the bank’s KYC process, automated machine checks screen customer transactions against third-party databases of politically exposed persons every month. Once there is a hit, the transaction is flagged and forwarded to the back office, where an associate reviews the involved people.
- Review ticket data, CRM & third-party sources
- Organize evidence & review for discrepancies
- Investigate mismatches
- Search web for more info, if needed
- Make final decision & file resolution comment
- Automated collection of data from ticket and databases
- Display summary of initial evidence
- Side-by-side comparison of relevant data
- Use agentic AI search for open-ended research scenarios
- Provide recommendations based on all collected evidence
- AI-drafted resolution comment for agent to review
The Assistant triggers inside the KYC case system when the back office associate clicks on a new KYC case and offers its help to the associate by doing the following:
Upon starting, the Assistant automatically gathers all available and relevant data from the KYC case and customer support system Zendesk. In addition, the Assistant collects information from predefined sources such as LexisNexis, Google, and LinkedIn.
The Assistant organizes all available evidence and displays it in a summary for the associate to inspect. It shows in detail which information has been collected, and any mismatches that have been detected. In addition, it lets the associate know which evidence is considered stronger or weaker.
For side-by-side comparisons, the Assistant displays relevant data next to each other, and points out discrepancies visually in order to simplify the task at hand.
In non-standard scenarios, where initial evidence has not delivered a clear conclusion, the associate can fall back on agentic AI to trigger and open web research. In that case, the locally running AI model reviews all data collected by the Assistant and identifies potential research angles, without instruction by the associate. These research angles are then performed one after the other and prepared for review by the associate. Any additional evidence that has been collected is linked for easy access. In the end, the associate can apply the generated research results to enhance the underlying AI model.
The Assistant provides a final recommendation based on all collected evidence and drafts a resolution comment for review including additional evidence. The associate can add or adjust this comment before submitting it.
A success message notifies the associate that the resolution comment has been successfully filed so they can proceed to the next task.
Explore our collection of Matterway Skills for different use cases that highlight the results & task steps before and after Matterway is implemented.
.png)
Investigate transactions that have been flagged to involve sanctioned persons or countries and decide whether the transaction should be approved or rejected.
.png)
Review broken wire transactions and take appropriate follow-up action to unblock the payment.
.png)
Generate contract renewal quotes by reviewing the customer’s eligibility for discounts by looking at various data sources.
Review & calculate policy renewal premiums for property & casualty insurance, considering various factors.
Reconcile investor accounts in Excel in a streamlined fashion while maximising process compliance.
Review training requests for employees, register them in the HR Suite, and finally purchase the training on the company’s intranet platform
European Regional Development Fund
A brand by Productive Mobile AWSM GmbH
All rights reserved.