Cleanlab · Agentic Access

Cleanlab Agentic Access

x-agentic-access generated

Cleanlab exposes 3 API operations that an AI agent could call, of which 3 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 write and 1 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.

AILLMTrustworthinessData QualityGuardrails

Operations: 3 Acting: 3 Human-in-the-loop: 0 Method: generated

By consequence

write 2 physical 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.

Method	Path	Consequence	Human-in-loop
POST	/api/v1/deployment/{model_id}/predict	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/cleanlab-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: 3
  by_action_class:
    acting: 3
  by_consequence:
    write: 2
    physical: 1
  human_in_the_loop_required: 0
operations:
- path: /api/v1/openai_trustworthy_llm/v1/chat/completions
  method: post
  operationId: createTrustworthyChatCompletion
  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/codex/projects/{project_id}/validate
  method: post
  operationId: validateResponse
  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/deployment/{model_id}/predict
  method: post
  operationId: predict
  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