KLOOM
Book a demo
PLATFORM
Morphic Identity EngineImmutable Evidence APIPoint-in-Time InvestigationsAgent Identity Layer
SOLUTIONS — BY INDUSTRY
National Security & IntelFinancial Intelligence & BankingCrypto & Web3 Compliance
BY MISSION
Sanctions & SDN ScreeningAdverse Media MonitoringOSINT Subject ResolutionContinuous Due Diligence & KYC
COMPANY
CareersContact
Book a demo
Solutions/ By mission/ Sanctions & SDN Screening
By mission

Screen names against every list — in the script they arrived in.

Kloom returns coherence and certainty as two independent axes per candidate — so your team can distinguish a disqualified non-match from a genuinely underdetermined one, and defend every cleared decision to a regulator.

Book a technical walkthrough
screening result · Name Intelligence v2 · 147 ms
query Mohamed Al-Rashid Arabic
محمد الراشد · lists: OFAC SDN, EU consolidated, UK sanctions
Tariq Al-Rashid SDN-3104
resolved
merge_confidence
0.91
merge_coherence likely
Mohamad Al Rashid SDN-4812
ambiguous
merge_confidence
0.61
merge_coherence possible
Mohammed Rashid SDN-2201
underspecified
merge_confidence
0.23
merge_coherence excluded
blocking_evidence: DOB: 1971-04-02 vs 1989-11-15
resolving_attributes: [date_of_birth, nationality]
candidates
3
resolved
1
ambiguous
1
01 · Where incumbent stacks break

A threshold is not a decision.
Evidence is.

Sanctions screening breaks in three compounding ways that no threshold adjustment can fix.

01

Threshold collapse

A single tunable threshold trades recall for precision blindly. Raise it and you miss matches transliterated differently on the list. Lower it and analysts drown in false positives. The score cannot tell you which candidates were disqualified by evidence and which were simply underdetermined.

threshold: 0.65 // reason: null
02

Non-replayable clearances

A customer is cleared on Tuesday. The OFAC list updates on Wednesday. Was the clearance still defensible? Without session pinning, re-running the query against the current graph does not reproduce the original decision — and a regulator asking you to prove it will know.

decision: "cleared" // evidence_basis: null
03

Cross-script list dropout

An Arabic-script name returns zero candidates against a Latin-script index. Translation at index time introduces naming ambiguity — عمر maps to "Umar" or "Omar" depending on convention — and that choice propagates silently. Sanctions lists carry names in every script; matching must too.

"محمد الراشد" → 0 results against SDN
02 · What Kloom provides

Four capabilities.
One defensible pipeline.

Blocking evidence and resolving attributes as separate fields

Every candidate carries blocking_evidence (predicates that disqualify it) and resolving_attributes (predicates that would resolve it but aren't yet known) as separate fields. Your team can distinguish a disqualified non-match from a genuinely underdetermined one.

blocking_evidence resolving_attributes per candidate

Replayable clearance decisions

Every adjudication is pinned to the graph version current at decision time. Re-run it six months later and you get the same result against the same evidence basis — because the evidence record is append-only and the session is addressed deterministically, not by snapshot copy.

session pinning append-only evidence regulator-defensible

Cross-script matching against every major list

Names are queried against OFAC SDN, EU consolidated, UK sanctions, UN, and bespoke lists in the script they arrived in — no lossy transliteration at index time. Cross-script retrieval is a query-time operation, not an index-time normalisation.

OFAC SDN EU consolidated UK & UN every script lists carry

Standing queries for list updates and re-screening

Register a standing query at onboarding. When any subscribed list updates — new designations, amendments, removals — the query re-evaluates automatically against the updated graph and fires an alert only when the evidence warrants it. No batch re-run required.

auto re-evaluation alert on change evidence payload
03 · Score anatomy

Every score decomposed. Blocking evidence inline.

Each candidate result carries per-component sub-scores — phonetic similarity, typographic tolerance, nickname conventions, initial handling, and cross-script translation — alongside the composite coherence and certainty values.

When a candidate is blocked, the blocking_evidence field names the disqualifying attribute — so a reviewer can override it, a regulator can audit it, and a false positive can be corrected without re-running the pipeline.

differentiation

“A reviewer can defend a decision without re-running the model.”

match result · SDN-3104 · 147 ms
Tariq Al-Rashid
OFAC SDN entry · DOB: 1969-08-14 · nationality: SY
COHERENCE 0.87
└─ phonetic
0.91
└─ typo
0.84
└─ nickname
0.73
└─ initial
0.88
└─ translation
0.86
CERTAINTY 0.91
└─ qualifying attributes 3 matched
└─ alignment name · DOB · nationality
blocking_evidence
null
match · review queue
Platform

Relevant platform capabilities

Name Intelligence

Original-script name matching feeding the cohesion and coherence phases. Cross-script retrieval at query time, not index-time normalisation.

Read the page

Append-only evidence

Every mention is appended, never overwritten. Blocking evidence and resolving attributes accompany every coherence, query, and alert response.

Read the page

Point-in-Time Investigations

Deterministic session pinning. Reproducible clearance decisions without a snapshot copy.

Read the page

Morphic Identity Engine

Continuous reshaping as evidence arrives — no destructive merges, every split and merge recomposable.

Read the page
Ready when you are

Book a technical walkthrough.

A demo runs against your sanctions lists and returns resolved candidates with decomposed scores your analysts can audit end to end. Thirty minutes, with engineering in the room.

Book a demo