Orderful Agentic Access
Orderful exposes 21 API operations that an AI agent could call, of which 12 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.
By consequence: 9 read and 12 safety-critical.
12 operations are classed safety-critical and should require human-in-the-loop approval at runtime.
Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.
By consequence
Highest-consequence actions
The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.
| Method | Path | Consequence | Human-in-loop |
|---|---|---|---|
| POST | /transactions | safety-critical | required |
| POST | /transactions/{transactionId}/deliveries/{deliveryId}/accept | safety-critical | required |
| POST | /transactions/{transactionId}/deliveries/{deliveryId}/fail | safety-critical | required |
| POST | /v3/convert | safety-critical | required |
| POST | /v3/deliveries/{deliveryId}/approve | safety-critical | required |
| POST | /v3/deliveries/{deliveryId}/fail | safety-critical | required |
| POST | /v3/labels | safety-critical | required |
| POST | /v3/polling-buckets/{id}/confirm-retrieval | safety-critical | required |
| POST | /v3/transactions | safety-critical | required |
| POST | /v3/transactions/confirm-delivery | safety-critical | required |
| POST | /v3/transactions/raw | safety-critical | required |
| POST | /v3/transactions/{transactionId}/acknowledgment | safety-critical | required |