Applied AI at work / Module 4
Module 4. Reviewing files and records for red flags with AI
Your role: General (any role). The exercises open on its variant. Change role
Time: 3.5 hours (17 minutes of video lessons, 140 minutes of exercise, 20 minutes of quiz). Your task in this module: review records against written rules and find the red flags planted in them. Sections 1 to 5 work through one example in depth, a KYC review of fictional investor files; section 6 gives the same workflow for every other role, and the exercise has a variant for each role. You use AI to build the checklist and the tests, confirm each flag in the data, and write the escalation note yourself.
In the finance variant you review 40 fictional investor files (individuals and companies) and find the 8 red flags planted in them: hidden beneficial owners, expired documents, an undeclared PEP, a sanctions near-match that the screening tool cleared, and incoherent sources of funds.
This module applies the method of module 3 to the work of a KYC or fund administration analyst. For the full legal content of AML/CFT in Luxembourg, the Primary Source AML/CFT course covers it in depth (https://primarysource.lu/courses).
All data in this module is fictional, including the two screening lists (TRAINING-SANCTIONS and TRAINING-PEP) and the countries "Republic of Vandria" and "Republic of Ostmark". You may paste it into any tool.
What you will be able to do
- Separate what AI may do in a KYC review (checklists, formulas, drafts) from what the analyst must decide (PEP and sanctions status, sign-off)
- Build a review checklist from Articles 1(7), 1(9), 1(10), 3(2) and 3-2(4) of the Law of 12 November 2004 and check it against the text
- Use structure-only prompts to get Excel tests for document expiry, subscription multiples, third-party payers and look-through ownership
- Identify hidden beneficial owners held through one or several controlled companies
- Review screening hits on name, date of birth and nationality rather than on the tool's score
- Write neutral findings with evidence and a legal anchor, and clear decoys with a recorded reason
4 video lessons, 17 minutes
- 4.1 Where AI helps in KYC review, and the legal anchors you check against 4:45
- 4.2 The six-step review workflow 4:11
- 4.3 The five red flag families, the decoys, and what to tell your manager 4:04
- 4.4 The same review in every role, and the exercise 3:33
Exercise: Review files for red flags
A variant for each role, opening on yours: General (any role). Fictional data, scored automatically against the answer key, with the model answer after you submit.
Module quiz
8 questions, pass mark 6. Passing it counts towards your course certificate.
Sources
- Law of 12 November 2004 on the fight against money laundering and terrorist financing, Articles 1(7), 1(9), 1(10), 3(1), 3(2), 3-2(4), 5(5), CSSF English consolidated text: https://www.cssf.lu/wp-content/uploads/L_121104_AML.pdf (page: https://www.cssf.lu/en/Document/law-of-12-november-2004/)
- Microsoft Learn, Data, privacy, and security for Microsoft 365 Copilot: https://learn.microsoft.com/en-us/copilot/microsoft-365/microsoft-365-copilot-privacy
- Microsoft Support, Get started with Copilot in Excel: https://support.microsoft.com/en-us/excel/copilot/get-started-with-copilot-in-excel
- Primary Source course catalogue: https://primarysource.lu/courses