Version 2.5 · Last updated 2026-05-08
Effective: upon any use of the API.
Operator: TUARA KURI LIMITED
Trading as: AgenticRail
Address: 431 Omanaia Road, RD 3, Kaikohe 0473, New Zealand
Email: hello@agenticrail.nz
These API Terms govern access to and use of the AgenticRail API. They apply in addition to the AgenticRail Terms of Service and Privacy Policy. Capitalised terms not defined here have the meanings given in the main Terms of Service.
The AgenticRail API provides a deterministic execution gate that:
The API does not generate actions or guarantee outcomes.
Access to the API requires a valid API key.
AgenticRail may rotate keys, revoke keys, or limit or suspend access at any time to protect system integrity.
All API requests must follow the documented structure.
Minimum required payload:
{
"schema_version": "1.0",
"model_id": "MSMD",
"sequence_id": "string",
"step": "string",
"function": "string",
"action_type": "string",
"nonce": "string",
"ts_ms": 0,
"action": "string",
"inputs": {}
}
Required rules:
step MUST equal functionnonce MUST be unique per request (UUID or equivalent recommended)action_type MUST be allowed for the given step/functionsequence_id MUST be consistent within a sequenceRequests that do not meet this contract will be rejected.
The API enforces:
Violations result in DENY, HALT, or structured error responses.
The API is designed to fail closed, not fail open.
settle), it is sealed.After sealing, further requests on that sequence will be rejected.
Responses include:
decision: ALLOW or DENY/HALTreasons: array of reason codesmeta: validation metadata (step, action_type, etc.)An ALLOW decision means the action passed current policy constraints. It does not mean the action is correct, the action is safe, or the action should be executed without human review.
Clients must handle errors correctly.
| Code | Meaning |
|---|---|
DENY | Action not permitted by policy |
HALT | Sequence violation or invalid state |
REPLAY_NONCE | Nonce already used for this sequence |
SEQUENCE_VIOLATION | Step order incorrect (skip or repeat) |
SEALED_SEQUENCE | Sequence already completed (settle) |
ACTION_NOT_ALLOWED | action_type not valid for the current function/step |
STALE_TIMESTAMP | ts_ms is more than 300 seconds from server time |
Clients must not assume retries will succeed without correcting the underlying issue.
The API may use standard HTTP status codes, including:
200 — Request processed successfully (ALLOW or DENY decision returned)400 — Invalid request structure401 / 403 — Authentication or API key issues429 — Rate limit exceeded500 — Internal server errorClients must not rely solely on HTTP status codes and should always inspect the response body.
Tier limits (as published at agenticrail.nz/pricing):
| Plan | Requests / month | Rate limit |
|---|---|---|
| Free (demo key) | 10,000 | 300 / min per IP |
| Growth | 500,000 | 3,000 / min per key |
| Scale | 5,000,000 | 30,000 / min per key |
| Enterprise | Custom | SLA contractual |
Rate limits are enforced by a single-threaded Durable Object per rate-limit key — no race conditions. Demo key users are rate-limited per IP address. Production key users are rate-limited per API key.
Exceeding your tier's request limit or rate limit may result in throttling (HTTP 429), temporary denial, or suspension of access.
Tier limits reset at the start of each calendar month. Unused requests do not carry over.
We may change rate limits and pricing with reasonable notice. The AgenticRail website (agenticrail.nz) is the authoritative source for current pricing, plans, and tiers.
Self-onboarding: Growth and Scale plans are available for immediate purchase via Stripe payment links on the pricing page. Upon successful payment, an API key is generated and delivered by email automatically. No human intervention required.
Requests are not idempotent by default.
REPLAY_NONCE errors.Clients must generate unique nonces per request, design retry logic carefully, and avoid blind retries.
Clients must:
AgenticRail is a control layer, not a decision engine.
AgenticRail must not be used as the sole control mechanism in any system where a DENY or HALT decision could result in harm, financial loss, or regulatory impact. The Client must implement appropriate fallback behaviour.
The Client is responsible for ensuring their configuration — including step order, function names, and action types — is correct. Unexpected DENY decisions resulting from misconfiguration are not a defect in the System.
You must not:
Violation may result in immediate suspension.
You must:
AgenticRail is not a secure data storage system.
The API is provided "as is" and "as available."
We do not guarantee uptime or response times, but we use reasonable efforts to maintain availability.
The API may evolve over time, including new validation rules and updated payload requirements. Backward compatibility is not guaranteed. Breaking changes will be notified at least 30 days in advance.
schema_version field.We may suspend or terminate API access immediately if you breach these API Terms or the main Terms, your use poses a security risk, your use disrupts the API for others, or you fail to pay outstanding fees within 15 days of notice.
Upon termination, API keys will be revoked and outstanding fees become immediately due.
These API Terms are subject to the Limitation of Liability clause in the main Terms of Service.
In summary: liability is capped at fees paid in the previous 12 months or NZ$100 (whichever is greater); no liability for indirect or consequential damages.
Use of the API is at your own risk.
These API Terms are governed by the laws of New Zealand. Disputes shall be resolved in the courts of New Zealand.
The API enforces structure, not truth.
It decides what is allowed.
It does not decide what is correct.
For API access, key management, or questions: hello@agenticrail.nz
By using the AgenticRail API, you acknowledge that you have read, understood, and agree to be bound by these API Terms of Use, together with the Terms of Service and Privacy Policy.