For Agents
Read employees, performance reviews, and goal records from Leapsome to feed BI dashboards, talent reviews, and agent-driven reporting workflows.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Leapsome 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 Leapsome API.
List employees on the Leapsome platform with role and department metadata
Retrieve completed and in-progress performance review records for analytics
Read goal records to track OKRs and individual objectives across the company
GET STARTED
Use for: List all employees in Leapsome, Retrieve recent performance reviews for analytics, Get the active goals for the company, Sync Leapsome reviews into a BI warehouse
Not supported: Does not handle payroll, recruiting, or write operations on reviews and goals — use for read-only employee, review, and goal access only.
Jentic publishes the only available OpenAPI specification for Leapsome API, keeping it validated and agent-ready. The Leapsome API exposes core read access to a performance management and employee development platform: agents can list employees, retrieve performance reviews, and read goal records. The surface is intentionally small and read-only, focused on syncing review and goal data into reporting tools or AI agents rather than authoring new content.
Sync review and goal data into a warehouse for cross-system people analytics
Power AI agents that summarise an employee's recent reviews and goals on demand
Patterns agents use Leapsome API for, with concrete tasks.
★ People Analytics Warehouse Sync
Centralise Leapsome data in a BI warehouse for cross-system people analytics. The agent calls /users for the employee list, /reviews for performance review records, and /goals for active objectives, then loads each result set into a warehouse table. Replaces brittle CSV exports and keeps the analytics layer current without manual reruns.
Call GET /users, /reviews, and /goals; load each response into the matching warehouse table and emit a summary of the row counts.
Manager Talent Review Brief
Generate a one-pager for a manager preparing a calibration session. The agent pulls the manager's direct reports from /users, fetches their recent reviews from /reviews, reads current goals from /goals, and renders a summary card per report. Removes hours of manual cross-referencing across the Leapsome UI.
Filter /users by managerId, then for each report join /reviews and /goals on userId and render a one-page summary.
Goal Progress Slack Reminder
Nudge employees about goals due this quarter. The agent reads /goals filtered to the current quarter, joins each goal to its owner via /users, and posts a personalised Slack reminder to anyone whose goals are still open. Lifts goal completion without managers having to chase manually.
Read /goals where due date is within the current quarter and status != 'completed', then DM each owner via Slack with the goal title and due date.
AI Agent Performance Summary via Jentic
An AI agent built on Jentic answers manager questions like 'show me how Alex has performed this year'. The agent searches Jentic for the matching Leapsome operation, reads the user, joins reviews and goals, and produces a narrative summary backed by the underlying records.
Through Jentic, search 'list leapsome reviews', execute /reviews filtered by userId, and combine with /goals to produce a year-to-date performance narrative.
3 endpoints — jentic publishes the only available openapi specification for leapsome api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/users
List employees on the platform
/reviews
List performance review records
/goals
List goals and OKRs
/users
List employees on the platform
/reviews
List performance review records
/goals
List goals and OKRs
Three things that make agents converge on Jentic-routed access.
Credential isolation
Leapsome API keys are stored encrypted in the Jentic vault and applied to the `Authorization` header only at execution time. The agent never has access to the raw key, so HR data access cannot leak through prompt or tool-call traces.
Intent-based discovery
Agents search Jentic with intents like 'list leapsome reviews' or 'get goals' and Jentic returns the matching Leapsome operation with its input schema, removing the need to read API docs.
Time to first call
Direct Leapsome integration: half a day to wire auth and three endpoints into a sync. Through Jentic: minutes — search, load schema, execute the read.
Alternatives and complements available in the Jentic catalogue.
Specific to using Leapsome API through Jentic.
Why is there no official OpenAPI spec for Leapsome API?
Leapsome does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Leapsome API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the Leapsome API use?
The Leapsome API uses an API key passed in the `Authorization` header. Through Jentic, the key sits encrypted in the credential vault and is added to the header at execution time, so it never appears in the agent's prompt or logs.
Can I read performance reviews from the Leapsome API?
Yes. GET /reviews returns review records with cycle, reviewer, and rating fields. The endpoint is read-only — review authoring still happens inside Leapsome's UI.
What are the rate limits for the Leapsome API?
The OpenAPI spec does not declare rate limits. Treat the API as a moderate-volume HR integration: warehouse-sync flows should run on a schedule with backoff rather than continuous polling.
How do I list goals through Jentic?
Run `pip install jentic`, search 'list leapsome goals', and execute GET /goals. The Jentic flow returns the goal records ready to filter by quarter or owner without manually constructing the request.
Does the Leapsome API let me create or update reviews and goals?
Not in this version of the spec. The exposed endpoints are read-only — GET /users, GET /reviews, and GET /goals. Use the Leapsome UI or contact Leapsome directly for write access.