Predibase · Agentic Access

Predibase Agentic Access

x-agentic-access generated

Predibase exposes 23 API operations that an AI agent could call, of which 12 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: 11 read, 10 write, and 2 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.

AILLMFine-TuningInferenceLoRA
Operations: 23 Acting: 12 Human-in-the-loop: 0 Method: generated

By consequence

read 11 write 10 physical 2

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
POST /deployments physical conditional
DELETE /deployments/{deploymentName} physical conditional

Source

Agentic Access

Raw ↑
generated: '2026-07-15'
method: generated
source: openapi/predibase-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: 23
  by_action_class:
    acting: 12
    connected: 11
  by_consequence:
    write: 10
    read: 11
    physical: 2
  human_in_the_loop_required: 0
operations:
- path: /v1/chat/completions
  method: post
  operationId: createChatCompletion
  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: /v1/completions
  method: post
  operationId: createCompletion
  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: /generate
  method: post
  operationId: generate
  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: /generate_stream
  method: post
  operationId: generateStream
  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: /finetuning/jobs
  method: post
  operationId: createFinetuningJob
  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: /finetuning/jobs
  method: get
  operationId: listFinetuningJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /finetuning/jobs/{jobId}
  method: get
  operationId: getFinetuningJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /finetuning/jobs/{jobId}/cancel
  method: post
  operationId: cancelFinetuningJob
  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: /repos
  method: post
  operationId: createRepo
  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: /repos
  method: get
  operationId: listRepos
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /repos/{repoName}
  method: get
  operationId: getRepo
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /repos/{repoName}
  method: delete
  operationId: deleteRepo
  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: /deployments
  method: post
  operationId: createDeployment
  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: /deployments
  method: get
  operationId: listDeployments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments/{deploymentName}
  method: get
  operationId: getDeployment
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /deployments/{deploymentName}
  method: delete
  operationId: deleteDeployment
  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: /datasets
  method: post
  operationId: createDataset
  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: /datasets
  method: get
  operationId: listDatasets
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /datasets/{datasetName}
  method: get
  operationId: getDataset
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /models
  method: get
  operationId: listModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /batch-inference/jobs
  method: post
  operationId: createBatchInferenceJob
  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: /batch-inference/jobs
  method: get
  operationId: listBatchInferenceJobs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /batch-inference/jobs/{jobId}
  method: get
  operationId: getBatchInferenceJob
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none