Waxell · Agentic Access

Waxell Agentic Access

x-agentic-access generated

Waxell exposes 12 API operations that an AI agent could call, of which 10 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: 2 read, 8 write, and 2 safety-critical.

2 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.

AI Agent GovernanceObservabilityPolicy EnforcementLLM TelemetryCost ManagementMCPAgent Runtime

Operations: 12 Acting: 10 Human-in-the-loop: 2 Method: generated

By consequence

read 2 write 8 safety-critical 2

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
PUT	/api/v1/observe/model-costs/{model_id}/	safety-critical	required
DELETE	/api/v1/observe/model-costs/{model_id}/	safety-critical	required

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/waxell-observe-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 12
  by_action_class:
    acting: 10
    connected: 2
  by_consequence:
    write: 8
    read: 2
    safety-critical: 2
  human_in_the_loop_required: 2
operations:
- path: /api/v1/observe/runs/start/
  method: post
  operationId: startRun
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/runs/{run_id}/complete/
  method: post
  operationId: completeRun
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/runs/{run_id}/llm-calls/
  method: post
  operationId: recordLlmCall
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/runs/{run_id}/steps/
  method: post
  operationId: recordStep
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/runs/{run_id}/spans/
  method: post
  operationId: recordSpan
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/runs/{run_id}/scores/
  method: post
  operationId: recordScore
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/prompts/{name}/
  method: get
  operationId: getPrompt
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/observe/policy-check/
  method: post
  operationId: checkPolicy
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/events/
  method: post
  operationId: recordEvent
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/observe/model-costs/
  method: get
  operationId: listModelCosts
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/observe/model-costs/{model_id}/
  method: put
  operationId: setModelCost
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v1/observe/model-costs/{model_id}/
  method: delete
  operationId: deleteModelCost
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required