TheheadlessATSthatrunsitself.

Every capability is a command your agent can call. Postings collect applications, assessments score themselves, automations move the routine motion. Humans make the decisions. Software does the rest.

Works in Claude ChatGPTClaude CodeCursorVS CodeDashboard
claude mcp add --transport http hiring-orchestrator https://www.hiringorchestrator.com/api/mcp
Ask your pipeline anything⌘K
youOpen a Senior PM req in Product
agentcreate_job → “Senior PM” · pipeline ready
youMove Maya to onsite
agent move_application_stage → Onsite · undo available
pipeline · PM role
Applied
Screen
Assess
Onsite
Offer

Auto-on

Thepipelinemoves.Youdecide.

Legacy ATSs are databases that wait for clicks. Orchestrator closes the loop: a published posting feeds stage one directly, the native assessment sends and scores itself, and automations you set in one sentence handle the routine motion. What reaches you is the part that deserves a human.

  • Hosted job board with structured apply, bot-gated, zero setup
  • Assessment stage scores back automatically with a full scorecard
  • Automations advance, tag, note, and notify. They never reject
  • Everything audit-logged with undo handles on every move
while you were in a meetingauto-on
09:14

Application received on the hosted board

j.lindqvist → Applied

09:14

Assessment invitation sent automatically

30-min multimodal · HiringTest

10:02

Scored. Composite 86, scorecard attached

fraud-checked · domains on record

10:02

Automation: score 80+ → advance to Interview, notify the team

undo handle t_4c1 · audit-logged

10:31

You: “prep me for the 2pm with Maya”

briefing: background, domain gaps, prior feedback

When you want eyes on it

Arealboard,oneconsumerofthesamecommands.

See your own funnel → sign in
Senior Product Manager · live funnel
Applied24
R. Okafor
J. Lindqvist
T. Reyes
Assessment11
M. Chen
86
A. Petrov
71
Interview5
S. Haddad
88
L. Moreau
82
Offer2
D. Kim
91
Hired3
P. Novak
89

Drag-and-drop board, candidate profiles, scorecards, settings. Every card shows who moved it: a person, an agent, or an automation. The UI calls the same 62 commands your agent does, which is the point. Headless means the interface is optional, not absent.

How it works

Connect.Import.Itruns.

01

Connect

Add the connector in Claude or ChatGPT, or run one command in Claude Code. OAuth handles the rest. No keys to wrangle, no seats to provision.

02

Import

Walk in with your whole pipeline. Promote your Greenhouse, Ashby, or Gem state into Orchestrator: jobs, candidates, stages, and history.

03

It runs

Postings collect applications. Assessments send and score themselves. Automations move the routine motion and tell you what needs a human. You decide; it executes.

Agent-native, not chatbot-bolted

Thesoftwareisthetoolset.

“Headless” here is 62 typed commands over the Model Context Protocol, with a Claude Skill that teaches the playbooks: triage, weekly review, req-to-offer, migration day one. Reads are instant. Writes are graded: routine moves carry an undo handle, and anything destructive asks first.

  • Native MCP server with OAuth, added like any Claude or ChatGPT connector
  • A Claude Skill with triage, weekly-review, and req-to-offer playbooks
  • An Ashby-parity REST API and outbound webhooks for everything else
  • Public command reference and llms.txt, generated from the live catalog
tool stream · audited
list_applicationsjob: Senior PM · 18 active
move_application_stageto Onsite · undo: t_9f2
send_assessmentinvite emailed · stage set
get_interview_briefingdomain gaps + prior feedback
extend_offerletter emailed · v2 terms
?reject_applicationawaiting confirmation

Natively connected

HiringTest assessments, in the pipeline

An assessment stage that runs a scored, fraud-checked, 30-minute multimodal assessment in-process. The composite and scorecard land back on the application automatically. Graded auto-advance moves strong candidates forward, and never rejects anyone for you.

HiringCase profiles, on the record

When a candidate has a published case, it surfaces on their ATS profile: verified endorsements and demonstrated work, candidate-controlled. The candidate-side network the incumbents can't offer.

Questions

Thehonestanswers.

What does headless actually mean here?+

The product is a capability layer, not an app. One capability layer powers the MCP server your agent calls, the REST API, the in-product copilot, and the UI. The interface is whichever one you're already in. Most ATSs added an API to a UI; this is built the other way around.

And auto-on?+

The routine motion runs without you touching it. A published posting collects applications straight into stage one. An attached assessment sends itself and scores flow back automatically. Automations advance, tag, note, and notify on triggers you set. The only thing that never automates is the decision: nothing here rejects a candidate on its own.

Is this a chatbot bolted onto an ATS?+

It's the inverse. The ATS is a set of typed capabilities, and the agent is the front door. Every action a recruiter takes in a legacy ATS is a tool an agent can call, scoped to your company, audit-logged, and reversible.

Do I have to give up a UI?+

No. There's a pipeline board, job and candidate views, and settings for the moments you want hands on the records. But the day-to-day runs from the agent you already live in.

Will it move candidates without me?+

Only upward, and only past thresholds you set. Stage moves carry an undo handle, destructive actions require confirmation, offer approvals are bound to the named approver's own account, and it never auto-rejects. We suggest, and you decide.

Runhiringfromtheagentyoualreadyuse.