For Agents
Retrieve candidate profiles, advance or reject applications, access interview scorecards, and query job and department data from a Greenhouse account.
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Greenhouse Harvest 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.
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh# 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 Greenhouse Harvest API API.
Search candidates by name, email, or application status across all jobs
Advance applications through interview stages or reject with configurable reasons
Retrieve structured interview scorecards with ratings and interviewer comments
Query open jobs with department, office, and hiring team associations
GET STARTED
Use for: I need to retrieve a candidate's application details, I want to advance an application to the next interview stage, List all open jobs in the Engineering department, Retrieve interview scorecards for a specific candidate
Not supported: Does not handle job board posting distribution, employee onboarding, payroll, or HRIS functions — use for recruiting data export and candidate pipeline management only.
Jentic publishes the only available OpenAPI document for Greenhouse Harvest API, keeping it validated and agent-ready.
Jentic publishes the only available OpenAPI specification for Greenhouse Harvest API, keeping it validated and agent-ready. Export and manage recruiting data across 20 endpoints covering candidates, applications, jobs, interviews, scorecards, and organizational structure. Advance or reject applications programmatically, retrieve structured interview scorecards, and access department and office hierarchies for reporting.
Access organizational hierarchy through departments and offices endpoints
Pull scheduled interview details including date, interviewers, and location
Patterns agents use Greenhouse Harvest API API for, with concrete tasks.
★ AI Agent Hiring Pipeline Automation
AI agents use the Greenhouse Harvest API through Jentic to automate hiring decisions without direct Greenhouse credentials. An agent searches for 'advance application to next stage', loads the schema for the advance endpoint, and moves qualified candidates forward based on scorecard ratings. The reject endpoint handles automated declinations with configurable reason codes.
Retrieve all applications for job ID J001 in the 'Technical Screen' stage, check their scorecard ratings, and advance those with average rating above 4 to 'On-Site'
Candidate Data Export
Export structured candidate data for analytics, compliance reporting, or syncing with downstream HRIS systems. The candidates endpoint returns profile information, application history, and current status across all jobs. Paginated responses support incremental sync patterns for large candidate databases without overwhelming system resources.
Retrieve all candidates who applied in the last 30 days and return their name, email, current application stage, and applied job title
Interview Scorecard Analysis
Access structured interview feedback through the scorecards endpoint to aggregate ratings, identify patterns in interviewer assessments, and generate hiring committee summaries. Each scorecard includes the interviewer, rating scales, attribute scores, and free-text comments tied to a specific interview for a candidate.
Retrieve all scorecards for candidate ID C001 and calculate the average overall rating across all interviewers
Job and Department Reporting
Build organizational hiring reports by querying jobs with their department and office associations. The jobs endpoint returns hiring team members, opening count, and status while departments and offices provide the org structure. Combined queries enable headcount planning dashboards and time-to-fill metrics by department.
List all open jobs grouped by department and return the job title, number of openings, and days since posting for each
20 endpoints — jentic publishes the only available openapi specification for greenhouse harvest api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/candidates
List all candidates
/candidates/{id}
Get a specific candidate
/applications
List all applications
/applications/{id}/advance
Advance an application to next stage
/applications/{id}/reject
Reject an application
/jobs
List all jobs
/scorecards
List interview scorecards
/scheduled_interviews
List scheduled interviews
/candidates
List all candidates
/candidates/{id}
Get a specific candidate
/applications
List all applications
/applications/{id}/advance
Advance an application to next stage
/applications/{id}/reject
Reject an application
Three things that make agents converge on Jentic-routed access.
Credential isolation
Greenhouse Harvest API tokens are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped access tokens — raw Harvest tokens never enter the agent's context.
Intent-based discovery
Agents search by intent (e.g., 'advance application to next interview stage') and Jentic returns matching Greenhouse Harvest operations with their input schemas, so the agent can call the right endpoint without reading Greenhouse's developer docs.
Time to first call
Direct Greenhouse integration: 2-3 days for token setup, pagination handling, and webhook configuration. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Lever API
Recruiting platform with opportunities-based pipeline, referral tracking, and offer management
Choose Lever when the organisation uses Lever as their ATS, or needs referral source tracking and opportunity-centric data model
SmartRecruiters API
Enterprise hiring platform with job board distribution and vendor marketplace
Choose SmartRecruiters for large enterprises needing built-in job board posting and third-party assessment integrations
Ashby API
Modern ATS with native analytics, scheduling, and candidate CRM
Choose Ashby for high-growth startups wanting built-in recruiting analytics without third-party BI tools
BambooHR API
Full HRIS with employee records, onboarding, and time-off management
Use BambooHR alongside Greenhouse to sync hired candidates into employee records and manage the post-offer onboarding workflow
Specific to using Greenhouse Harvest API API through Jentic.
Why is there no official OpenAPI spec for Greenhouse Harvest API?
Greenhouse does not publish an OpenAPI specification for the Harvest API. Jentic generates and maintains this spec so that AI agents and developers can call Greenhouse Harvest 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 Greenhouse Harvest API use?
The API uses HTTP Basic authentication with your Harvest API token as the username and an empty password. Tokens are generated per-user in Greenhouse settings with configurable permission scopes. Through Jentic, the Harvest API token is stored in the MAXsystem vault so agents authenticate without handling the raw token.
Can I advance or reject applications through the Greenhouse Harvest API?
Yes. POST /applications/{id}/advance moves an application to the next configured stage in the job's interview plan. POST /applications/{id}/reject marks an application as rejected with an optional rejection reason ID and email notification flag. Both operations require the application ID and appropriate API token permissions.
What are the rate limits for the Greenhouse Harvest API?
Greenhouse enforces a rate limit of 50 requests per 10 seconds for the Harvest API. Exceeding this returns HTTP 429 with a Retry-After header. List endpoints support pagination via the per_page parameter (max 500) and Link headers for cursor-based traversal of large result sets.
How do I retrieve interview scorecards through Jentic?
Search Jentic for 'get interview scorecards for candidate', load the schema for GET /scorecards with the application_id filter parameter, and execute. The response includes each scorecard's overall recommendation, attribute ratings, and interviewer comments. Install with pip install jentic and authenticate at https://app.jentic.com/sign-up.
What candidate data can I access through the Harvest API?
GET /candidates returns candidate profiles including name, email addresses, phone numbers, tags, and linked applications. GET /candidates/{id} provides full detail for a single candidate. The applications sub-resource shows which jobs they applied to, their current stage, and rejection status if applicable.
/jobs
List all jobs
/scorecards
List interview scorecards
/scheduled_interviews
List scheduled interviews