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/ Agent Identity Layer
Platform

Give your agents structured uncertainty — not a match verdict.

Kloom returns merge_coherence, confidence, blocking_evidence, and resolving_attributes in the response envelope — the same uncertainty surface a human reviewer would act on. Agents can navigate it, branch on it, and escalate when confidence is insufficient to act.

Book a technical walkthrough
tool exchange · agent_session_1892
→ kloom.entity_coherence
name "Zhang Wei"
dob "1981-04-12"
lists ["OFAC SDN", "EU"]
← response
merge_coherence "likely"
confidence 0.61 ← below threshold
blocking_evidence []
resolving_attributes
└─ predicate "date_of_birth"
└─ resolution_value "1981-04-12"
└─ instruction "supply to confirm match"
status "accepted_pending_review"
agent branch
confidence 0.61 < threshold 0.80 → route to curator queue
merge_coherence
likely
confidence
0.61
status
pending_review
01 · Where agentic identity fails

A boolean is not
what an agent needs.

Three failure modes that make traditional identity APIs unsafe to act on inside an agentic pipeline.

01

Boolean verdicts

Most identity APIs return a match/no-match. An agent that receives a boolean cannot distinguish "disqualified by evidence" from "insufficient evidence to qualify." Both look the same. Only one should block — and the agent has no way to know which is which.

{"match": false} // reason: null // certainty: hidden
02

Non-auditable agent reasoning

When an agent makes a compliance decision based on identity data, the chain of reasoning should trace to citable evidence. If the identity API returns a black box, the agent's reasoning is also a black box. A regulator asking "why did the agent clear this transaction?" deserves a real answer.

agent.decision = "clear" // evidence_trail: null
03

Polling for state changes

An agent monitoring a customer for new sanctions exposure needs to know when something changes. Without standing queries, the agent polls — an expensive loop with false-negative windows between each check. A newly designated entity may remain undetected until the next poll fires.

while True: resolve() // interval: 3600s // gap: up to 1h
02 · What the agent surface provides

Navigate uncertainty.
Don’t collapse it.

Structured uncertainty surface

Merge coherence, confidence, blocking evidence, and resolving attributes all arrive in the response envelope. An agent can branch on any of these fields — route on certainty, inspect blocking evidence before escalating, or surface the resolving attributes as justification for a positive decision.

merge_coherence + confidence blocking_evidence resolving_attributes

Evidence-traceable reasoning

Every claim the agent makes about an entity traces to a citable mention in the immutable evidence layer. The agent's chain of reasoning — "I cleared this transaction because matching attributes X, Y, and Z from sources A, B, and C" — is reproducible and auditable end to end.

mention_id per result append-only record full audit trail

Standing queries and webhook delivery

Register a standing query at onboarding. When a customer's resolved entity changes state — a newly matching sanctions pattern, a previously uncertain cluster crossing a certainty threshold — the webhook fires. No polling, no false-negative windows, no re-running the workflow from scratch.

event-driven no polling structured payload

First-class tool surface

Kloom integrates with agent toolchains as a named tool: entity_coherence, evidence, alert_subscribe, curator_queue. Each tool call has a typed schema, a typed response, and a contract the agent can reason about. The API is designed to be consumed by an LLM-driven orchestrator, not just a human developer.

typed tool schema typed response orchestrator-native
03 · Agent screening flow

Uncertain result — not a no-match. There is a difference.

An initial resolve call returns merge_coherence of "likely" — consistent with a real match — but confidence of 0.61, below the threshold to act. A boolean identity API returns false. Kloom returns a structured response the agent can reason about: fetch more evidence, check what is missing, escalate with context.

Every step the agent takes — the initial resolution, the evidence fetch, the escalation — carries a citable mention_id. The agent’s chain of reasoning is auditable end to end against the append-only evidence record.

differentiation

"Most identity APIs hand an agent a boolean. Kloom hands it a structured uncertainty surface — which is what an agent actually needs to act safely."

screening workflow · 3 steps
step 1 Initial resolution
→ entity_coherence({name: "Zhang Wei", dob: "1981-04-12"})
← merge_coherence: "likely" · confidence: 0.61 · status: "accepted_pending_review"
step 2 Fetch resolving evidence
→ evidence({entity_id: "ent_9041"})
mentions: 2 retrieved
missing: ["date_of_birth", "nationality"]
confidence still insufficient after fetch
step 3 Curator queue task created
→ curator_queue({status: "open"})
task_id: "task_8821"
mention_ids attached · chain auditable
Platform

Relevant platform capabilities

Morphic Identity Engine

The cluster layer that generates the structured uncertainty surface. Coherence, certainty, blocking evidence, and resolving attributes are products of the probabilistic cluster model.

Read the page

Immutable Evidence API

The immutable evidence layer that makes agent reasoning auditable. Every mention_id an agent follows traces to a citable, permanent mention record.

Read the page

Continuous Due Diligence & KYC

The primary use case for the agent surface: agentic onboarding and continuous monitoring workflows where standing queries trigger re-screening without manual intervention.

Read the page
Ready when you are

Book a technical walkthrough.

Thirty minutes with engineering. We run a live agentic screening workflow — resolve, fetch evidence, escalate — and walk the full uncertainty surface and audit trail at each step.

Book a demo