Look up one recent decision by the decision_id from the API response or

the outcome.produced webhook. The analytics log is bounded and ephemeral: a 404 means ‘rotated out of the recent window or never existed’ — billing truth lives…

GET /v1/decisions/{id}

cURL

curl --request GET \
  --url 'https://api.nsr.stateset.com/v1/decisions/{id}' \
  --header "X-API-Key: $STATESET_NSR_API_KEY"

200

{
  "batch": true,
  "billable": true,
  "cited_rules": [
    "string"
  ],
  "confidence": 7.5,
  "cost_micros": 1,
  "decision": "string",
  "decision_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "dropped_citations": [
    "string"
  ],
  "external_ref": "string",
  "latency_ms": 250,
  "missing_predicates": [
    "string"
  ],
  "outcome": "string",
  "query": "string",
  "request": {
    "action": "string",
    "authorization_goal": {
      "args": [],
      "name": "Two-Person Tent",
      "negated": true
    },
    "confidence_threshold": 7.5,
    "facts": [
      {
        "confidence": null,
        "predicate": null,
        "source": null
      }
    ],
    "hydrate_org_context": true,
    "max_depth": 1,
    "mode": "string",
    "query": "string",
    "rules": [
      {
        "category": null,
        "constraints": null,
        "description": null,
        "effect": null,
        "enabled": null,
        "id": null,
        "if": null,
        "name": null,
        "priority": null,
        "then": null
      }
    ]
  },
  "request_policy_hash": "string",
  "timestamp": "2026-08-31T14:22:05Z"
}

the outcome.produced webhook. The analytics log is bounded and ephemeral: a 404 means ‘rotated out of the recent window or never existed’ — billing truth lives in the metering pipeline.

Required scope: read

Path parameters

id · string · required

Response

DecisionRecord

batch · boolean · required

True when the decision came through /v1/decisions/batch.

billable · boolean · required

cited_rules · string[] · required

Rule ids cited in the proof chain.

confidence · number (double)

The confidence the decision reported, in [0, 1]. Stored so calibration can bucket decisions by what they claimed and compare against what actually happened (see outcome).

cost_micros · integer (int64) · required

decision · string · required

approved | denied | refused.

decision_id · string

The decision_id returned in the API response and carried by the outcome.produced webhook — the correlation key for audits.

dropped_citations · string[]

Org rules that fired during hydration but were dropped from the proof as unrelated — the audit record of standing-rule noise per decision.

external_ref · string

Optional client-supplied correlation key (their order id, case id, claim number…). This is what closes the outcome loop from REAL events: a chargeback or override webhook knows the order id, not our decision_id, so POST /v1/decisions/outcome-by-ref records the outcome by this key. None when the caller didn’t supply one.

latency_ms · integer (int64) · required

missing_predicates · string[]

Deduped predicate names from a refused decision’s refusal.missing_facts — the KB coverage gaps that blocked it. Empty for approvals/denials and safety-gated refusals (which carry none).

outcome · string

The real-world outcome, recorded AFTER the fact via POST /v1/decisions/{id}/outcome: honored (the decision held up), reversed (e.g. an approved refund was charged back), overridden (a human changed it), or escalated. None until reported. This is the ground truth that turns confidence from a heuristic into a calibrated, measurable number.

query · string · required

The decision query, truncated to 200 chars for memory hygiene.

request · object

Show request

action · string

authorization_goal · object

Show authorization_goal

args · Arg[] · required

name · string · required

negated · boolean

Negation-as-failure for a rule CONDITION: not fraud_flagged(?o, ?r). Meaningful only on rule conditions (ignored on facts and conclusions). Defaulted and skipped-when-false so existing payloads are unchanged. Without this the negation was silently dropped and the condition read as POSITIVE — a fraud-flagged subject slipped a not fraud_flagged guard.

confidence_threshold · number (double)

facts · RecursiveChatFactInput[]

Show RecursiveChatFactInput

confidence · number (double)

predicate · RecursiveChatPredicateInput · required

source · string

hydrate_org_context · boolean

max_depth · integer

mode · string

query · string · required

rules · RecursiveChatRuleInput[]

Show RecursiveChatRuleInput

category · string

constraints · any[]

description · string

effect · object

enabled · boolean

id · string

if · RecursiveChatPredicateInput[] · required

name · string · required

priority · integer (int32)

then · RecursiveChatPredicateInput[] · required

request_policy_hash · string

sha256:<hex> over the request-scoped policy the decision was evaluated against (see DecisionProof::request_policy_hash) — lets an audit confirm a replay uses the same policy inputs.

timestamp · string (date-time) · required

Status codes

Code	Meaning
200	The decision record
401	Unauthorized — missing or invalid credentials
403	Forbidden — the key/token lacks the required scope
404	Not in the retained window
429	Rate limited — see Retry-After / X-RateLimit-Reset

cURL

curl --request GET \
  --url 'https://api.nsr.stateset.com/v1/decisions/{id}' \
  --header "X-API-Key: $STATESET_NSR_API_KEY"

200

{
  "batch": true,
  "billable": true,
  "cited_rules": [
    "string"
  ],
  "confidence": 7.5,
  "cost_micros": 1,
  "decision": "string",
  "decision_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "dropped_citations": [
    "string"
  ],
  "external_ref": "string",
  "latency_ms": 250,
  "missing_predicates": [
    "string"
  ],
  "outcome": "string",
  "query": "string",
  "request": {
    "action": "string",
    "authorization_goal": {
      "args": [],
      "name": "Two-Person Tent",
      "negated": true
    },
    "confidence_threshold": 7.5,
    "facts": [
      {
        "confidence": null,
        "predicate": null,
        "source": null
      }
    ],
    "hydrate_org_context": true,
    "max_depth": 1,
    "mode": "string",
    "query": "string",
    "rules": [
      {
        "category": null,
        "constraints": null,
        "description": null,
        "effect": null,
        "enabled": null,
        "id": null,
        "if": null,
        "name": null,
        "priority": null,
        "then": null
      }
    ]
  },
  "request_policy_hash": "string",
  "timestamp": "2026-08-31T14:22:05Z"
}