Every autonomous AI action requires a receipt

Autonomous execution without governance is unauthorized execution

AI agents are gaining repository write access, merging pull requests, modifying infrastructure, and executing multi-step workflows. Most produce zero admissibility evidence. That creates provenance gaps, unverifiable reasoning chains, authorization drift, and untraceable actions at machine speed.

Issue your first receipt in 30 seconds

No account required for the public evaluation endpoint. Submit a claim with evidence and get back a signed Decision Receipt.

curl -X POST https://decrec.summitcognitive.ai/v1/evaluate \
  -H "Content-Type: application/json" \
  -d '{
    "claim_id": "my-first-receipt",
    "entity": "my-org/my-repo",
    "claim": "AI agent requests merge authority for PR #42",
    "sources": [
      {"id": "ci", "type": "ci", "uri": "https://ci/run/1",
       "confidence": 0.9, "content": "All tests pass"},
      {"id": "review", "type": "code_review", "uri": "https://pr/1",
       "confidence": 0.85, "content": "Approved by maintainer"}
    ]
  }'

Response includes a full DecisionReceipt with replay hash, policy checks, evidence hashes, and an Ed25519 attestation. See full API docs →

Get your API key

Enter your email to receive an API key instantly. No credit card required.