Google Cloud Natural Language · Agentic Access

Google Cloud Natural Language Agentic Access

x-agentic-access generated

Google Cloud Natural Language exposes 5 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: 5 write.

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.

Entity RecognitionGoogle CloudMachine LearningNatural Language ProcessingSentiment AnalysisText Analysis

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

By consequence

write 5

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/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: 5
  by_action_class:
    acting: 5
  by_consequence:
    write: 5
  human_in_the_loop_required: 0
operations:
- path: /documents:analyzeSentiment
  method: post
  operationId: analyzeSentiment
  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: /documents:analyzeEntities
  method: post
  operationId: analyzeEntities
  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: /documents:classifyText
  method: post
  operationId: classifyText
  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: /documents:analyzeSyntax
  method: post
  operationId: analyzeSyntax
  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: /documents:annotateText
  method: post
  operationId: annotateText
  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