Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the intelliHR Public API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhumanforce.com%2Fintellihr" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhumanforce.com%2Fintellihr" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with intelliHR Public API.
Create and update business entities, business units, and locations
Define custom field definitions that extend employee records
Administer jobs, job changes, probation, and job requirements
Record extended leave and set employment conditions
Manage pay grades and default remuneration components
GET STARTED
Drive onboarding templates and forms
Patterns agents use intelliHR Public API for, with concrete tasks.
★ Agent HR Administration via Jentic
AI agents administer an intelliHR platform through Jentic without holding the API key in context. An agent searches by intent, receives the matching operation schema, and creates org structure, records leave, or updates jobs end to end. Jentic injects the key at execution time, so the agent never sees the secret while it maintains HR records.
Search Jentic for 'create an intelliHR business unit', load the POST /business-units schema, and create the unit with Jentic-managed credentials
Organizational Structure Setup
An agent builds out the org backbone of an intelliHR tenant: it creates business entities and business units, adds locations, and defines the custom fields that capture the data each employee record needs. Because intelliHR exposes explicit entity, unit, and custom-field operations, the agent can stand up a consistent structure without a human clicking through admin screens.
Call POST /business-entities and POST /business-units to build the org structure, then define fields via custom-field-definitions
Leave and Job Administration
An agent keeps employment records current by recording extended leave, setting employment conditions, and reflecting job changes as they happen. intelliHR exposes extended-leave, employment-condition, and job operations directly, so the agent can process HR events promptly instead of queueing them for a person to enter later.
Call POST /extended-leave to record leave and GET /employment-conditions to read the conditions that apply
137 endpoints — jentic publishes the only available openapi specification for intellihr public api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/business-entities
List all business entities
/business-entities
Create a new business entity
/business-units
List all business units
/extended-leave
Create an extended leave record
/employment-conditions
List all employment conditions
/custom-field-definitions
List all custom field definitions
/business-entities
List all business entities
/business-entities
Create a new business entity
/business-units
List all business units
/extended-leave
Create an extended leave record
/employment-conditions
List all employment conditions
/custom-field-definitions
List all custom field definitions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the intelliHR Public API by hand means setting the Authorization API key header and sequencing the many entity, job, and leave operations across the platform yourself. Through Jentic you install once, import the intelliHR Public API from the API Directory, store the key, and your agent calls it.
Permission scoping
The intelliHR Public API puts each record id in the URL path, so a rule can pin your agent to one business unit or job and the operations you choose. You decide which operations it may call, so create, update, and delete calls stay out unless you grant them.
Credential isolation
Your intelliHR API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a business unit' or 'record extended leave', and Jentic returns the matching intelliHR operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using intelliHR Public API through Jentic.
Why is there no official OpenAPI spec for intelliHR Public API?
Humanforce does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call intelliHR Public API via structured tooling. It is validated against the live API and kept up to date. To run it on your own infrastructure, install Jentic One from its GitHub repo.
What authentication does the intelliHR Public API use?
The intelliHR Public API authenticates requests with an API key sent in the Authorization header, per its OpenAPI spec. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I record extended leave with the intelliHR Public API?
Yes. Record extended leave with POST /extended-leave, list jobs with GET /jobs, and read employment conditions with GET /employment-conditions.
How do I create a business unit with the intelliHR Public API through Jentic?
Search Jentic for 'create an intelliHR business unit', load the returned POST /business-units operation with its input schema, and your agent creates the unit with credentials injected at call time.
Is there an intelliHR MCP server?
You don't need an MCP server to give your agent the intelliHR Public API. Jentic connects it directly from the API Directory: import it, store your key, and your agent calls it, discovering operations on demand instead of loading a separate server's tool definitions into its context.
Can I limit what my agent is allowed to do with the intelliHR Public API?
Yes. The intelliHR Public API puts each record id in the URL path, so a rule can scope your agent to one business unit or job and the operations you pick, such as reading records without editing them. You choose which operations it may call, so create, update, and delete calls stay out unless you add them.
Know of an official OpenAPI document? Contribute it →
For Agents
Manage business entities, units, jobs, leave, and custom fields on an intelliHR platform. Requests authenticate with an API key.
Use for: I want to create a new business unit in intelliHR, Record extended leave for an employee, List all jobs in the organization, Add a custom field to employee records
Not supported: Does not process payroll payments or handle time-and-attendance capture. Use for HR records, jobs, and organizational structure only.
Jentic publishes the only available OpenAPI specification for intelliHR Public API, keeping it validated and agent-ready. The intelliHR Public API gives AI agents programmatic control over an intelliHR people-management platform. Agents manage the organizational backbone, creating and updating business entities, business units, and locations, and defining custom fields that extend employee records. They administer jobs and job changes, record extended leave, set employment conditions and probation, and manage pay grades and remuneration components. Requests authenticate with an API key in the Authorization header.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>