For BSA / AML Officer
Alert Triage
Work one transaction-monitoring alert against the customer’s file and twelve months of history, then close it or escalate it for a filing.
Almost every alert my team reads is a false positive. The handful that are not is the entire conversation with my regulator.
Work one alert yourself: read the free screen, pay hours for the lookups you think you need, and close or escalate it citing the facts. Only then does the board show what the generator planted — and what your call cost against the reference.
Your attempt
Synthetic data — no real customer, account or transaction
Alert
A-8971·R-STR-01—Three or more cash deposits just under the reporting threshold within ten days
Triggering transactions
| id | date | channel | amount | where |
|---|---|---|---|---|
T-213 | 2026-04-16 | cash in | 9,440.00 USD | branch BR-052 |
T-217 | 2026-04-21 | cash in | 8,950.00 USD | branch BR-052 |
T-219 | 2026-04-22 | cash in | 8,880.00 USD | branch BR-052 |
KYC file
C-9647Oakhill Kitchen Group
kyc.account_opened- 2019-07-11
kyc.business_type- pizzeria
kyc.country- United States
kyc.customer_type- business
kyc.expected_activity- Cash-intensive food service; daily takings deposited most trading days.
kyc.expected_monthly_cash- 86,000.00 USD
kyc.kyc_refreshed- 2026-03-13
kyc.pep- no
kyc.prior_alerts- 4
kyc.prior_sars- 0
kyc.remittance_declared- none declared
kyc.stated_income- 492,000.00 USD
Twelve-month summary
| month | cash in | cash out | wires in | wires out | ACH in | ACH out | txns |
|---|---|---|---|---|---|---|---|
| 2025-05 | 42,400 | 0 | 0 | 0 | 0 | 13,935 | 18 |
| 2025-06 | 38,160 | 0 | 0 | 0 | 0 | 12,582 | 19 |
| 2025-07 | 44,260 | 0 | 0 | 0 | 0 | 15,928 | 18 |
| 2025-08 | 41,680 | 0 | 0 | 0 | 0 | 13,940 | 18 |
| 2025-09 | 44,950 | 0 | 0 | 0 | 0 | 15,498 | 17 |
| 2025-10 | 35,860 | 0 | 0 | 0 | 0 | 13,284 | 19 |
| 2025-11 | 42,370 | 0 | 0 | 0 | 0 | 12,792 | 19 |
| 2025-12 | 39,280 | 0 | 0 | 0 | 0 | 13,776 | 19 |
| 2026-01 | 39,860 | 0 | 0 | 0 | 0 | 13,940 | 19 |
| 2026-02 | 39,280 | 0 | 0 | 0 | 0 | 12,718 | 18 |
| 2026-03 | 36,510 | 0 | 0 | 0 | 0 | 11,693 | 19 |
| 2026-04 | 71,720 | 0 | 0 | 0 | 0 | 14,218 | 18 |
Counterparties on screen
CP-1outbound48 txns103,976.00 USDCP-2outbound12 txns60,331.50 USD
Reporting threshold in this jurisdiction: 10,000.00 USD
Hours spent so far: 0.50. 8 replies left.
The machine you are inside
1The task
Triage one transaction-monitoring alert on a synthetic customer: read the screen, pay analyst-hours for any lookups, then close it with a reason or escalate it with a typology, citing the facts.
2Legal actions
One JSON object per reply — a lookup (a month’s history, a counterparty, prior alerts, documents) or a disposition (close with a reason, escalate with a typology), citing only ids you were shown. Anything else is refused and still costs a turn.
3The grader
Regenerates the alert from the seed, compares the disposition and the cited ids to what the generator planted, and charges the hours. Deterministic Python: no model, no human, no prose read anywhere.
4The score that moves
Over half for nothing slipping through, a quarter for clearing it within the reference hours, a fifth for citing the facts that decide it. A missed escalation zeroes all three.
This reward: Miss nothing, then clear it fast