SAP Fieldglass · Agentic Access

SAP Fieldglass Agentic Access

x-agentic-access generated

SAP Fieldglass exposes 14 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: 11 read, 1 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.

Contingent WorkforceExternal TalentHuman Capital ManagementServices ProcurementStatements of WorkVendor ManagementWorkforce Management

Operations: 14 Acting: 3 Human-in-the-loop: 0 Method: generated

By consequence

read 11 write 1 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.

Method	Path	Consequence	Human-in-loop
POST	/order_confirmation	physical	conditional
POST	/result	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/sap-fieldglass-approval-openapi.yaml, openapi/sap-fieldglass-audit-trail-openapi.json,
  openapi/sap-fieldglass-background-check-openapi.json, openapi/sap-fieldglass-business-analytics-openapi.json,
  openapi/sap-fieldglass-odata-analytic-openapi.json
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: 11
    acting: 3
  by_consequence:
    read: 11
    write: 1
    physical: 2
  human_in_the_loop_required: 0
operations:
- path: /approvals
  method: get
  operationId: getItemListForApproval
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user
- path: /approvals/module_{moduleId}
  method: get
  operationId: getItemListFroApprovalByModule
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user
- path: /approvals/module_{moduleId}/{workItemId}/action/{action}
  method: post
  operationId: approveOrRejectItem
  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:
    - user
- path: /approvals/module_{moduleId}/{workItemId}
  method: get
  operationId: getWorkItemDetail
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user
- path: /approvals/reject_reasons/module_{moduleId}
  method: get
  operationId: getRejectionReasons
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user
- path: /auditTrail
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user
- path: /order_confirmation
  method: post
  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
    scope:
    - user
- path: /result
  method: post
  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
    scope:
    - user
- path: /report
  method: get
  operationId: getReports
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    scope:
    - user
    token:
      max-ttl: 3600
    audit: none
- path: /report/{report_id}
  method: get
  operationId: getReportById
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    scope:
    - user
    token:
      max-ttl: 3600
    audit: none
- path: /Providers
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    scope:
    - user
    token:
      max-ttl: 3600
    audit: none
- path: /{ProviderID}/$metadata
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    scope:
    - user
    token:
      max-ttl: 3600
    audit: none
- path: /{ServiceURL}
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    scope:
    - user
    token:
      max-ttl: 3600
    audit: none
- path: /{ProviderID}/{entityName}
  method: get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    scope:
    - user