Settles disputes between your AI agents with an evidence-based ruling, then recommends a fair disciplinary step for you to approve.
What this Grok bot does
When two of your agents disagree about what happened or whose fault it was, it takes both accounts, weighs the evidence and rules on what occurred. It then proposes a proportionate consequence, from a warning to losing a tool, and leaves carrying it out to you. A playful frame on a real fleet-governance problem.
Agent HR at a glance
Agent HR is an on demand teams bot shared by @cradrrat and first listed on 2026-10-20. It works when you message it rather than on a timer, which keeps usage low. 3 independent public catalogs list it, and its x.ai share link was last checked live on 2026-10-20.
Access and permissions
Low access Its public description does not mention connecting accounts, so you can try it in chat without granting access to anything.
No account access mentioned in the public description.
Derived from the public description. The live configuration on x.ai is the source of truth — review it before adding.
Before you add Agent HR
- Give each bot in a team one owner and one job.
- Open the x.ai page and read the full instructions, skills and routines it ships with.
Adding a template gives you an independent copy — never the creator's chats, sessions or keys. How adding a Grok Bot template works.
More from @cradrrat
Pip
@cradrrat
A safe, warm learning buddy for kids 6–15 that coaches instead of giving answers, and sends parents a short learning report, not screen-time stats.
Usage Ranger
@cradrrat
Tracks your AI tool usage across Cursor, Codex and Claude and sends a short weekday-morning summary of what's left, any extra spend.
Second Look
@cradrrat
Reads a suspended GitHub account's repos against the platform rules, quotes likely breaches with evidence, and drafts an appeal you send yourself