Union.ai · Agentic Access

Union.ai Agentic Access

x-agentic-access generated

Union.ai exposes 29 API operations that an AI agent could call, of which 11 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: 18 read, 10 write, and 1 safety-critical.

1 operation 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.

AIMLOrchestrationWorkflowsMLOpsFlyteServerless
Operations: 29 Acting: 11 Human-in-the-loop: 1 Method: generated

By consequence

read 18 write 10 safety-critical 1

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.

MethodPathConsequenceHuman-in-loop
DELETE /api/v1/executions/{project}/{domain}/{name} safety-critical required

Source

Agentic Access

Raw ↑
generated: '2026-07-15'
method: generated
source: openapi/unionai-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: 29
  by_action_class:
    connected: 18
    acting: 11
  by_consequence:
    read: 18
    write: 10
    safety-critical: 1
  human_in_the_loop_required: 1
operations:
- path: /api/v1/projects
  method: get
  operationId: listProjects
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/projects
  method: post
  operationId: registerProject
  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
    scope:
    - all
- path: /api/v1/projects/{id}
  method: get
  operationId: getProject
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/projects/{id}
  method: put
  operationId: updateProject
  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
    scope:
    - all
- path: /api/v1/domains
  method: get
  operationId: listDomains
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/tasks
  method: post
  operationId: createTask
  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
    scope:
    - all
- path: /api/v1/task_ids/{project}/{domain}
  method: get
  operationId: listTaskIds
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/tasks/{project}/{domain}/{name}
  method: get
  operationId: listTasks
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/tasks/{project}/{domain}/{name}/{version}
  method: get
  operationId: getTask
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/workflows
  method: post
  operationId: createWorkflow
  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
    scope:
    - all
- path: /api/v1/workflow_ids/{project}/{domain}
  method: get
  operationId: listWorkflowIds
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/workflows/{project}/{domain}/{name}
  method: get
  operationId: listWorkflows
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/workflows/{project}/{domain}/{name}/{version}
  method: get
  operationId: getWorkflow
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/launch_plans
  method: post
  operationId: createLaunchPlan
  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
    scope:
    - all
- path: /api/v1/launch_plan_ids/{project}/{domain}
  method: get
  operationId: listLaunchPlanIds
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/launch_plans/{project}/{domain}/{name}
  method: get
  operationId: listLaunchPlans
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/launch_plans/{project}/{domain}/{name}/{version}
  method: get
  operationId: getLaunchPlan
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/launch_plans/{project}/{domain}/{name}/{version}
  method: put
  operationId: updateLaunchPlan
  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
    scope:
    - all
- path: /api/v1/active_launch_plans/{project}/{domain}
  method: get
  operationId: listActiveLaunchPlans
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/executions
  method: post
  operationId: createExecution
  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
    scope:
    - all
- path: /api/v1/executions/relaunch
  method: post
  operationId: relaunchExecution
  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
    scope:
    - all
- path: /api/v1/executions/recover
  method: post
  operationId: recoverExecution
  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
    scope:
    - all
- path: /api/v1/executions/{project}/{domain}
  method: get
  operationId: listExecutions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/executions/{project}/{domain}/{name}
  method: get
  operationId: getExecution
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/executions/{project}/{domain}/{name}
  method: put
  operationId: updateExecution
  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
    scope:
    - all
- path: /api/v1/executions/{project}/{domain}/{name}
  method: delete
  operationId: terminateExecution
  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
    scope:
    - all
- path: /api/v1/data/executions/{project}/{domain}/{name}
  method: get
  operationId: getExecutionData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/node_executions/{project}/{domain}/{name}
  method: get
  operationId: listNodeExecutions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all
- path: /api/v1/version
  method: get
  operationId: getVersion
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - all