Beam · Agentic Access

Beam Agentic Access

x-agentic-access generated

Beam exposes 6 API operations that an AI agent could call, of which 5 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: 1 read, 1 write, and 4 physical.

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.

ServerlessGPUPythonInferenceContainers

Operations: 6 Acting: 5 Human-in-the-loop: 0 Method: generated

By consequence

read 1 write 1 physical 4

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	/endpoint/id/{id}	physical	conditional
POST	/endpoint/{name}	physical	conditional
POST	/endpoint/{name}/v{version}	physical	conditional
POST	/taskqueue/{name}	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/beam-cloud-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: 6
  by_action_class:
    acting: 5
    connected: 1
  by_consequence:
    physical: 4
    read: 1
    write: 1
  human_in_the_loop_required: 0
operations:
- path: /endpoint/{name}
  method: post
  operationId: invokeNamedEndpoint
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /endpoint/{name}/v{version}
  method: post
  operationId: invokeNamedEndpointVersion
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /endpoint/id/{id}
  method: post
  operationId: invokeEndpointById
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /taskqueue/{name}
  method: post
  operationId: submitTaskByName
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/task/{task_id}/
  method: get
  operationId: getTaskStatus
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/task/cancel/
  method: delete
  operationId: cancelTasks
  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