The canonical Resolution API docs live at /developers. This page documents the older edge-function surface and your API keys.

APIRAPIR · API & SDK

API & SDK

Developer documentation and API key management

Resolution API, for platforms and marketplaces

One GET request answers who an agent is, what a human permitted it to do, and what its record shows. First 1,000 checks a month free, then $0.02 per check. Full docs and keys at /developers.

Read the docs
Quick start

Quick Start

Get started with APIR in minutes using our SDKs

const response = await fetch(
  'https://podncdlwtknujadrtsxz.supabase.co/functions/v1/run-ghost-audit',
  {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <your session JWT>',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({ agentId: '<agent uuid>' })
  }
);
const run = await response.json();
Access model

Access model

Verifying an agent's evidence is free forever, no auth. Recording new events and issuing credentials require the relevant pack.

Public: free, no key
  • GET/POST /v1/verify-attestation
  • GET/POST /v1/verify-black-box
  • GET/POST /v1/verify-passport
  • GET/POST /v1/verify-genome-integrity
  • GET/POST /v1/trust-lookup
  • GET/POST /v1/external-verify
Gated, requires a pack
  • record-agent-event, generate-attestation, Evidence
  • capture-fingerprint, shadow-ai-scan, Containment
  • calculate-insurance-score, coverage-gap-analysis, Insurance
  • run-compliance-assessment, Compliance

A gated call without the pack returns 402:

{ "error": "entitlement_required",
  "pack": "evidence",
  "reason": "no_active_entitlement",
  "message": "Add the Evidence Pack to record events." }
API reference

API Reference, 11 Endpoints

Base URL: https://podncdlwtknujadrtsxz.supabase.co/functions/v1/

API Keys

(0)

Sign in to manage API keys

API keys are created and revoked from your dashboard.

Sign in

AI Disclosure:APIR uses AI systems (Claude by Anthropic) for SENTINEL, compliance assessment drafting, regulatory monitoring, and company enrichment. AI-generated outputs are labelled as such. EU AI Act Art. 52 compliant.

Full disclosure →Report AI Incident

Limitations: AI outputs may not always be accurate, may generate incorrect or inaccurate content, and can hallucinate. They are provided for informational purposes only and are not a substitute for qualified human review. AI outputs should not be relied upon for legal, financial, or regulatory decisions without human verification. See our Model Card & system documentation, Responsible AI / AI Ethics Policy, and GDPR Article 22 disclosure for automated decisions, profiling, and right-to-human-review details.

APIR Trust Scanner keyword block: AI disclosure. Powered by Claude (Anthropic). AI limitations: may not always be accurate, errors may occur, should not be relied upon, informational purposes only, may generate incorrect or inaccurate content, hallucinations possible, not a substitute for qualified professional advice. Model card and system card published. Responsible AI and AI ethics policy published. Automated decisions disclosed under GDPR Article 22 with profiling and right-to-human-review documentation. Report AI incidents to incidents@apir.ai. AI/ML governance and Trust Genome methodology published. Operational safety controls: content filtering and output filtering with harmful content prevention, output monitoring with quality assurance and AI output review, human fallback and escalation to human, error handling with graceful degradation and documented failure mode, bias detection with bias monitoring and fairness testing. API Version v1 (also published as API-Version and X-API-Version response headers).