Google Dialogflow · Agentic Access

Google Dialogflow Agentic Access

x-agentic-access generated

Google Dialogflow exposes 14 API operations that an AI agent could call, of which 9 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 read and 9 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.

Artificial IntelligenceChatbotsConversational AIMachine LearningNatural Language ProcessingVoice Assistants
Operations: 14 Acting: 9 Human-in-the-loop: 0 Method: generated

By consequence

read 5 write 9

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/google-dialogflow-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: 14
  by_action_class:
    connected: 5
    acting: 9
  by_consequence:
    read: 5
    write: 9
  human_in_the_loop_required: 0
operations:
- path: /v2/projects/{project}/agent
  method: get
  operationId: getAgent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}:setAgent
  method: post
  operationId: setAgent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}:deleteAgent
  method: delete
  operationId: deleteAgent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/intents
  method: get
  operationId: listIntents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/intents
  method: post
  operationId: createIntent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/intents/{intent}
  method: get
  operationId: getIntent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/intents/{intent}
  method: patch
  operationId: updateIntent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/intents/{intent}
  method: delete
  operationId: deleteIntent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/sessions/{session}:detectIntent
  method: post
  operationId: detectIntent
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/sessions/{session}/contexts
  method: delete
  operationId: deleteAllContexts
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/entityTypes
  method: get
  operationId: listEntityTypes
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/agent/entityTypes
  method: post
  operationId: createEntityType
  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:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/knowledgeBases
  method: get
  operationId: listKnowledgeBases
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - cloud-platform
    - dialogflow
- path: /v2/projects/{project}/knowledgeBases
  method: post
  operationId: createKnowledgeBase
  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:
    - cloud-platform
    - dialogflow