Sanctions screening hits cleared on the evidence, with every possible match sent to a person.
Bluegrass builds sanctions screening review systems for banks, credit unions and fintechs. False positives that differ from the customer or payment on decisive identifiers are cleared with a written rationale, and every possible match goes to an analyst.
Screening tools are tuned to miss nothing, so the great majority of hits are false positives, and proving each one false accounts for most of a sanctions program's cost.
What screening review involves today
When a name resembles a sanctions list entry, an analyst has to decide whether it is the same person or entity. They compare identifiers and context, then record why the hit was discounted or escalate it, often against a payment cut-off.
Rescreening after list updates brings the work back, and adverse media adds articles to judge. Because the decisions repeat and the evidence is structured, AI can do this consistently, provided a person decides every case that is not clear-cut.
How automated screening review works
- 01
Collect the hit
Each hit arrives with the listed entry and the customer or payment details from your screening system, along with the customer's KYC record.
- 02
Compare the identifiers
Names, aliases, dates of birth, nationalities, identification numbers and vessel details are compared field by field, allowing for transliteration and name order.
- 03
Read the context
The system reads payment message fields and parties, and judges whether each adverse media article concerns the customer and matters to your risk.
- 04
Clear or escalate
A hit that differs on decisive identifiers is cleared with a rationale citing them; anything uncertain, including every possible true match, goes to an analyst with the comparison laid out.
- 05
Record the decision
Every disposition is written back to the screening or case system with its evidence, showing why each hit was cleared and by whom.
Where people stay in the loop
Possible true matches always go to a person, and blocking or rejecting a payment stays with your sanctions team. Automatic clearance comes one category at a time, and only once its accuracy is measured on your past decisions.
The systems it works with
The system works alongside your screening engine, reading its hits and writing dispositions back, so your lists, thresholds and audit trail stay where they are.
When to build it, and when to buy it
Screening vendors increasingly offer AI-assisted disposition of their own hits, and if yours does it well for your hit types, it should be the first option you consider.
A custom build makes sense when hits from several tools need one consistent review, when your rationale standard exceeds a vendor's default, or when screening should share records with KYC reviews and alert investigations.
We hold no reseller agreements, partner quotas or revenue share with any vendor, so a recommendation to buy is made on its merits.
What this work costs you today
A quick way to put a number on the problem before talking to anyone, using your own figures rather than ours.
Enter your volume and the minutes each one takes to see what the work costs in a year.
The numbers stay in your browser and are not stored or sent anywhere. Bring the figure to the first call, since it is the baseline any system should be measured against.
Questions about sanctions screening review
- Could the system clear a true match?
- It clears a hit only when decisive identifiers differ, and every uncertain case goes to an analyst. Your sanctions team decides which categories qualify, after accuracy is measured on your past dispositions.
- Does it change our screening thresholds?
- Thresholds stay as your screening program sets them. The system reviews the hits those thresholds produce, so it adds a consistent second look rather than loosening the net.
- Can it review adverse media as well?
- It judges whether each article concerns your customer and whether the allegation is relevant, then summarizes it with a link and leaves relevant hits to an analyst.
Related systems
A senior team that has done this before
We are a small, entirely senior team with fifty years of combined AI engineering, multiple granted patents and Y Combinator founders, from Yale, MIT, McKinsey, Goldman Sachs, Microsoft and Vista Equity Partners. The people who scope your work are the people who write the code.
Selected work
We built the AI transformation roadmap for a top-50 P&C brokerage, and it is saving the firm millions of dollars in vendor fees it did not need to pay.
Clients include some of the largest banks, RIAs, fintechs and AI labs, as well as a top-3 P&C carrier, a top-10 P&C brokerage, a top-5 trucking brokerage, a leading specialty MGA and a leading trucking MGA.
We run only 3 to 5 engagements at a time, so that every client works directly with the senior team.
About the team- Dozens
- of insurance companies, RIAs, banks and fintechs we have worked with
- 50 yrs
- combined AI engineering experience
- 10+ Patents
- granted to members of the team
- 100%
- of the IP we build is assigned to you
Find out whether this is worth building for your business.
A 30-minute call with an engineer usually shows whether this is worth building. Within a week you will have a free written point of view, including whether a packaged product would serve you better.