ADP · Agentic Access

ADP Agentic Access

x-agentic-access generated

ADP exposes 11 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: 8 read, 2 write, and 1 safety-critical.

1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.

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.

BenefitsHCMHRPayrollWorkforce

Operations: 11 Acting: 3 Human-in-the-loop: 1 Method: generated

By consequence

read 8 write 2 safety-critical 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	/events/hr/v1/worker.terminate	safety-critical	required

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/adp-payroll-openapi.yml, openapi/adp-workers-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: 11
  by_action_class:
    connected: 8
    acting: 3
  by_consequence:
    read: 8
    write: 2
    safety-critical: 1
  human_in_the_loop_required: 1
operations:
- path: /payroll/v1/payroll-outputs
  method: get
  operationId: listPayrollOutputs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payroll/v1/payroll-outputs/{payrollOutputID}
  method: get
  operationId: getPayrollOutput
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payroll/v1/payroll-outputs/{payrollOutputID}/worker-outputs
  method: get
  operationId: getPayrollWorkerOutputs
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payroll/v1/payroll-instructions
  method: get
  operationId: listPayrollInstructions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payroll/v1/payroll-instructions
  method: post
  operationId: createPayrollInstruction
  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: /hr/v2/workers
  method: get
  operationId: listWorkers
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /hr/v2/workers/{aoid}
  method: get
  operationId: getWorker
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /hr/v2/workers/{aoid}/work-assignments
  method: get
  operationId: getWorkerWorkAssignments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /events/hr/v1/worker.hire
  method: post
  operationId: hireWorker
  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: /events/hr/v1/worker.terminate
  method: post
  operationId: terminateWorker
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /core/v1/organization-departments
  method: get
  operationId: listDepartments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none