Hiring Agent
Reads every application that arrives, ranks it against the role rather than against the last CV the recruiter happened to like, and hands a person the one decision that is genuinely theirs. Written for an HR services firm where the bottleneck was never judgement and always throughput: 1,840 applications a month against 34 open roles, screened by three people who each read differently on a Friday than on a Monday. Six stations, run as a loop: what station 6 learns about who stayed changes what station 2 ranks on.
{{ g.n }}
{{ g.name }} · {{ g.sub }}
{{ g.desc }}
Subagents ({{ g.acount }})
{{ a.name }}{{ a.code }}{{ a.name }}{{ a.auto }}{{ tk }}
The workbench · subagents send notes, you make the human calls
SUBAGENT NOTES
{{ nt.ini }}{{ nt.who }} {{ nt.text }}
YOUR TASKS · HUMAN IN THE LOOP
{{ g.t1 }}
{{ g.t2 }}
{{ g.tnote }}
{{ g.btn }}
{{ g.wait }}
YOUR TASKS · NONE AT THIS STEP
{{ g.was }}
{{ g.ev1L }}{{ g.ev1V }}
{{ g.ev2L }}{{ g.ev2V }}
{{ g.ev3L }}{{ g.ev3V }}
✓
Cleared for full autonomy{{ g.sign }}
Put a person back on this step
How to read this map
{{ lg.code }}{{ lg.text }}
A person is in the loop wherever a human outcome becomes somebody's word. Five of the six stations refuse to proceed on their own, Shortlist Ranking, Interview Setting, Offer Deciding, Joiner Onboarding and Retention Reading, and those are the five a person carries. Everywhere else the subagents run at volume and reach you only when they cannot settle something.
The loop closes
Station 6 does not end the year. A scorecard change accepted after a cohort read is the scorecard station 2 ranks against and station 3 draws its questions from, which is why the same mis-hire only happens to this pipeline once.