Post a job to Recruitee via its ATS API — create an offer with a title, description, requirements, locations, department, work model and application-form location picker. Also creates talent pools. BYOK-only.
Recruitee is an applicant tracking system, and one of the 54 tools hyreflow connects to Claude, ChatGPT and other AI assistants. Through hyreflow, an AI agent can run 4 actions: 2 that look something up and 2 that create or change records. Recruitee runs on your own Recruitee account: hyreflow charges no credits for it, and Recruitee bills you as before.
Through hyreflow, an AI agent can run 4 Recruitee actions: 2 that look something up and 2 that create or change records. Recruitee runs on your own Recruitee account: hyreflow charges no credits for it, and Recruitee bills you as before.
| Recruitee action | What it does | Cost through hyreflow |
|---|---|---|
| Create job | Creates or changes a record | no hyreflow credits |
| Set job state | Creates or changes a record | no hyreflow credits |
| List departments | Looks something up | no hyreflow credits |
| List locations | Looks something up | no hyreflow credits |
One credit is priced on the pricing page. The full price list for every tool is in the pricing tables.
2 hyreflow skills call Recruitee as part of the run. A skill is a whole pipeline your agent already knows, end to end.
use whenthe same role has to be opened in more than one applicant tracking system and you are tired of typing it out in each
use whenyou have a client's job description or your own brief, and what goes on the careers page has to be written for the candidate, not for the client's file
hyreflow ships a written playbook for Recruitee, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Recruitee docs →Recruitee calls a job an offer, and the same endpoint creates either a real job or a talent pool.
Recruitee is BYOK-only. Connect your own Recruitee token and your company (the acme in
acme.recruitee.com, or the numeric company ID) in Integrations; there is no managed-key fallback and
the write costs 0 Hyreflow credits. A Recruitee token
is personal and per-company: it carries exactly the permissions of whoever minted it, and acts in their
name. list_departments is the free connection check: it verifies the key and returns the departments a department_id comes from.
create_job(payload) posts an offer. Required: title, description, location_ids, and
requirements (optional when kind is talent_pool).
title (required) — the offer title.description (required) — the offer description.location_ids (required) — array of Recruitee location ids, required even for a remote role.requirements — required for a job, optional for a talent pool.kind — job (default) or talent_pool.department_id — assigns the offer to an existing department.on_site / hybrid / remote (one of them required) — the work model shown on the careers
site. At least one must be true; none of the three defaults to true.visibility_options — defaults to ["locations_question"], adding a location picker to the application form.locations_question / locations_question_type (single_choice default or multiple_choice) /
locations_question_required.hyreflow tools execute recruitee_create_job --payload '{
"title": "Senior Platform Engineer",
"location_ids": [12345],
"description": "<p>Own the deployment platform.</p>",
"requirements": "<p>Kubernetes, CI/CD pipelines, five years of platform work.</p>",
"hybrid": true
}'
The offer id is offer.id; offer.slug is what appears in the careers URL.
location_ids comes fromThey are numeric Recruitee location ids, and list_locations returns them for free — search by city or
name with query and use each match's id. A new account starts with one location; add others under
Settings → General → Locations. There's no way to pass a location as a string on create.
title, description,
requirements, location_ids, and that one of on_site/hybrid/remote is true.kind is the only thing separating a job from a talent pool — read it back before executing.Recruitee's API accepts none of salary, employment type, category, experience, education, hours,
pipeline template, open questions, followers, hiring managers, or status on create — those are
read-only on the response and set inside Recruitee. Whether a fresh offer lands as draft or published
isn't part of Recruitee's documented contract either.
A created offer is a draft. set_job_state(offer_id) takes it live on the careers site:
hyreflow tools execute recruitee_set_job_state --payload '{"offer_id": 567441}'
state also accepts draft, closed and archived. Recruitee moves an offer with a per-transition
endpoint rather than a writable status field, so status stays read-only on the offer itself.
Yes. hyreflow is a connector for Claude, ChatGPT and other AI assistants. Once hyreflow is connected, you ask for the outcome in plain language and the assistant calls Recruitee for you. hyreflow exposes 4 Recruitee actions this way.
Yes. Recruitee runs on your own Recruitee account. You connect it to hyreflow once, hyreflow charges no credits for the calls, and Recruitee bills you as before.
Recruitee runs on your own Recruitee account: hyreflow charges no credits for it, and Recruitee bills you as before.
Add the hyreflow MCP server to your assistant and sign in. hyreflow calls the Recruitee API directly and exposes its actions as tools the assistant can run, so there is no separate Recruitee server to install.
Connect hyreflow to Claude or ChatGPT and ask for the outcome. It reads the playbook above before it makes a single call.