Claude-subagent
Hvorfor denne subagent
Skævhed i løn- eller forfremmelsesdata er reel, men let at overse og farlig at fejllæse. Denne spotter scanner anonymiserede HR-data for mønstre, som et menneske bør se på.
Hvert fund kommer med sine forbehold: stikprøvestørrelse, dataens begrænsninger og en tydelig note om, at dette er et signal til menneskelig gennemgang, ikke en dom. Den hjælper et HR- eller jurateam med at vide, hvor de skal kigge, uden at foregive, at tallene beviser hensigt.
Sådan kører den
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Used at step 01 to kick off the pipeline.
Eksempel på output
json// Sample output // (generated when the pipeline finishes) Report statistical gaps in the HR data by group, always with sample size and a stated caveat; flag for human review and never assert intent or causation.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.