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
Platform/ Immutable Evidence API
Platform

Every output, backed by addressable, reproducible evidence.

Blocking evidence and resolving attributes arrive in the response envelope — without a second call. The append-only evidence record means any decision, from any point in time, is fully citable.

Book a technical walkthrough
response envelope · sdk/query · 142 ms
status "underspecified"
query "Andrey Volkov"
candidates [3 results]
BLOCKING_EVIDENCE
└─ predicate "birth_date"
└─ predicate_shape "attribute"
└─ conflict_type "hard"
└─ confidence_impact "high"
└─ values[0] "1989-11-15"
└─ values[1] "1971-04-02"
RESOLVING_ATTRIBUTES
└─ predicate "employer"
└─ resolution_value "high"
└─ options ["ClearPay Ltd" ×4]
└─ instruction "Add an employer constraint to narrow the candidate set"
session "sess_abc123" · graph_version "v_3"
per-result
inline
evidence record
append-only
second call
not required
01 · Where most systems fall short

A score without evidence
is not an answer.

Three structural problems that make downstream systems — human or agentic — unsafe to act on.

01

Explainability as an afterthought

Debug logs are not audit trails. When a reviewer asks why the system decided what it decided, the answer should not require access to internal tooling, log aggregation, or a support ticket. If the explanation is not in the response, the response is not complete.

"why": "check the logs" // endpoint: /internal/debug
02

The overwrite model

Most identity systems commit to a resolved entity and overwrite it as new records arrive. The source data may persist — but the entity as it stood at decision time does not. When a regulator asks "what did the system treat as this person last October?", that boundary is gone.

entity.members: [recomputed] // prior boundary: gone
03

Audit as reconstruction

"Show me the evidence basis from last Tuesday" should be a one-call operation. In most systems it requires re-running the pipeline against an archived snapshot, hoping the snapshot exists, and hoping the pipeline has not changed. That is forensic reconstruction — not auditability.

// no stable evidence address // re-run and hope
02 · What the evidence layer provides

Explainability as output shape.
Not a debug feature.

Mention-level addressability

Every mention the system has ever seen is individually addressable. Query a cluster and receive the mention_id for each contributing mention. Pull the mention and you get the original source passage, its provenance, and the attributes extracted from it — no intermediary.

unique id per mention original passage attribute provenance

Append-only record

No observation ever overwrites another. New evidence appends to the record. The original mention that drove a clearance decision six months ago is still there, exactly as the system saw it — accessible to the same API surface that created it.

append-only no overwrites original preserved

Blocking evidence and resolving attributes inline

Both fields arrive in the response envelope without a second call. Downstream systems — human or agentic — can branch on evidence quality, escalate underdetermined cases, and cite the basis of a decision without accessing internal tooling.

blocking_evidence field resolving_attributes field no second call

Session migration reports

A long-running investigation pins a graph version. On refresh, you get a structured report of how the entities and conflicts in your working set changed — splits, merges, weight changes, anchors — so you can absorb new evidence deliberately instead of being silently re-resolved underneath you.

migration report split · merge · reweight session-scoped
03 · Audit infrastructure

Two streams — one lean, one forensic.

Stream A (Operational) is a metadata-only record — operation, principal, target, graph versions, outcome — with subject-identifying payload stripped at write time. It's GDPR-clean by content: once the mention store compacts, its identifier references no longer resolve to personal data.

Stream B (Forensic) mirrors that metadata and adds a pointer (payload_artifact_uri + hash) to the full payload, held in a WORM-capable store — the regulator-facing reconstruction surface. Which stream a mission writes to is fixed by its legal_basis: general → lean only, regulated → forensic.

Optional cryptographic chaining links entries in either stream — each entry’s hash incorporates its predecessor’s, so deleting or altering any entry breaks the chain forward.

The forensic stream is the complete, ordered record a regulator’s tooling can reconstruct decisions from — not a pipeline re-run.

audit stream schema · two-stream model
STREAM A · LEAN (audit_log_lean)
audit_id"audit_8821"
operation"mention_ingest"
principal"svc_ingestor_02"
target"entity / ent_4821"
graph_version_before"v20"
graph_version_after"v21"
outcome"accepted"
timestamp"2026-05-14T09:22:11Z"
request_id"req_77c1"
payloadstripped at write← GDPR-clean
STREAM B · FORENSIC (audit_log_forensic_metadata
+ WORM payload store)
audit_id"audit_8821"
operation"mention_ingest"
principal"svc_ingestor_02"
target"entity / ent_4821"
graph_version_before"v20"
graph_version_after"v21"
outcome"accepted"
timestamp"2026-05-14T09:22:11Z"
request_id"req_77c1"
payload_artifact_uri"s3://…/audit/8821"← full payload
payload_artifact_hash"sha256:3f8a…c904"
routing
lean · forensic
chaining
optional
scope
spans both
Platform

Relevant platform capabilities

Morphic Identity Engine

The cluster layer that operates over the evidence record. Probabilistic cluster decisions, non-destructive merges, typed conflict resolution — all grounded in the append-only evidence substrate.

Read the page

Point-in-Time Investigations

Deterministic session pinning over the evidence layer. Every query inside a session resolves against a pinned graph version — reproducible against the same evidence basis weeks later.

Read the page

Compliance

How the append-only model interacts with data-subject rights requests (GDPR deletion / rectification), data residency posture, and the forensic audit stream under regulatory review.

coming soon
Ready when you are

Book a technical walkthrough.

Thirty minutes with engineering. We run a live query, show the response envelope with blocking evidence and resolving attributes populated, and walk the audit stream for an adjudication decision.

Book a demo