Quickstart

A score in one call.

Authenticate with a scoped API key in the X-API-Key header and post the telemetry for one human-AI interaction. The response is synchronous and documented.

cURL# 1 · score one human-AI interaction $ curl -X POST api.cohesionauth.com/v1/score \ -H "X-API-Key: $COHESION_API_KEY" \ -H "Content-Type: application/json" \ -d '{"operator_id":"op_alice","session_id":"sess_42", "domain":"financial","interaction":{ ... }}' # 200 OK · judgment score envelope { "jis": 82.4, "dimensions": { "escalation_integrity": 88, ... }, "compliance": { "band": "proficient", "status": "compliant", "article14_met": true } }
Two scoring paths

DRS routes the decision, JIS scores the router.

Use both together. The Decision Risk Score routes each AI-assisted decision; the Judgment Independence Score measures whether the reviewer is a trustworthy router.

POST /v1/decision/score

Submit one AI-assisted decision for Decision Risk Score routing. Returns the decision risk score, the routing decision, policy trigger evidence, and an audit identifier.

cURL# route one AI-assisted decision $ curl -X POST api.cohesionauth.com/v1/decision/score \ -H "X-API-Key: $COHESION_API_KEY" \ -d '{"operator_id":"analyst-0042","domain":"financial", "decision":"modified","modification_extent":0.31}' # 200 OK · routing recommendation { "decision_risk_score": 0.27, "routing_decision": "auto" }

POST /v1/score

Score the human-AI interaction telemetry and return the Judgment Independence envelope across the seven dimensions, the band, and the decay projection.

cURL# 1 · score one human-AI interaction $ curl -X POST api.cohesionauth.com/v1/score \ -H "X-API-Key: $COHESION_API_KEY" \ -H "Content-Type: application/json" \ -d '{"operator_id":"op_alice","session_id":"sess_42", "domain":"financial","interaction":{ ... }}' # 200 OK · judgment score envelope { "jis": 82.4, "dimensions": { "escalation_integrity": 88, ... }, "compliance": { "band": "proficient", "status": "compliant", "article14_met": true } }
Built for compliance engineering

Designed to be cited, not just called.

Judgment envelopes

Score responses carry documented judgment payloads and request metadata. Signed receipts are issued from the DRS gate path and receipt service.

Score envelope

API key authentication

Scoped API keys per environment, sent in the X-API-Key header. Rotate without downtime. Keys never appear in evidence receipts.

X-API-Key

Synchronous scoring

Scores return in band on the same request. No polling, no webhooks required for the common path.

Single round trip

Typed SDKs

First party clients for TypeScript and Python, generated from the same schema as the docs.

2 languages

Mapped to the spec

Each dimension in the response maps to a clause in the specification and a regulatory citation.

Spec v1.3.0

Observable

Latency and uptime are published. Incidents are posted to the status page with a timeline.

Live status
Beyond the score

The evidence a regulator, an auditor, or a buyer asks for.

The scoring API returns the number. These services turn that live evidence into the artifacts other people need: a signed report, an exportable receipt, an append-only reasoning chain, and an early-warning velocity signal. Each runs on its own dedicated subdomain and reuses your existing API key.

Regulator report

A signed compliance report that maps your live oversight evidence to US and EU AI oversight law and NIST AI RMF 1.0. Generated on demand, ready to hand to a regulator or an auditor.

report-worker

DDQ kit

Answers thirteen AI-oversight question categories from standard vendor security questionnaires (CAIQ, SIG, VSQ) using your measured behaviour, not asserted policy. Speeds procurement review.

report-worker

Signed evidence receipt

An exportable signed per-decision evidence artifact serialized from an existing decision record. Anyone with the receipt can check whether the contents changed after COHESION issued it.

receipt-worker

Append-only evidence chain

Capture a reviewer's reasoning before the AI answers, then bind it into a per-org HMAC hash chain. The reveal-gate keeps the AI output sealed until the human commits, so the record cannot be back-fit.

reasoning-worker

Judgment velocity

A predictive slope over a reviewer's recent Judgment Independence Scores, so a reviewer drifting toward rubber-stamping is caught before the score crosses the oversight floor, not after.

velocity-worker

Receipt checker

A customer, auditor, or buyer can paste an exportable receipt into the checker and see whether the signature still matches the receipt contents. The checker does not reveal receipts the person does not already have.

Tamper-evident
GET/v1/reports/{org_id}/regulatorSigned regulator compliance report mapped to US and EU AI oversight law and NIST AI RMF (report-worker).
GET/v1/reports/{org_id}/ddqSigned DDQ kit answering CAIQ, SIG, and VSQ AI-oversight categories from live telemetry (report-worker).
GET/v1/decisions/{decision_id}/receiptSigned, exportable per-decision oversight evidence receipt (receipt-worker).
POST/v1/receipts/verifyVerify a receipt the caller already holds; this does not search or reveal receipts (receipt-worker).
GET/v1/receipts/public-keysFetch public ECDSA verification keys for receipt signatures; private key material is never returned (receipt-worker).
POST/v1/reasoning/captureCapture a reviewer's pre-AI reasoning into the append-only HMAC evidence chain (reasoning-worker).
GET/v1/reasoning/decision/{request_id}Reveal-gated decision detail; the AI output stays sealed until the human commits (reasoning-worker).
GET/v1/velocityPredictive Judgment Independence Score velocity for a reviewer (velocity-worker).
Reference

Selected endpoints.

A sample of the scoring API surface. The full reference, schema, and error catalog live in the docs.

POST/v1/decision/scoreReturn a Decision Risk Score and a routing recommendation for one AI-assisted decision.
POST/v1/scoreScore one human-AI interaction and return the Judgment Independence envelope.
POST/v1/score/batchScore multiple interactions in a single signed request.
GET/v1/organization/independence-trendReturn recent reviewer-independence trend rows for the authenticated organization.
GET/v1/operator/{id}/profileRetrieve a reviewer's Judgment Independence Score band over time.
GET/v1/admin/audit/verify-chainVerify the signature and hash chain of the issued evidence receipts.

Request access and score your first interaction.