Bias in pay or promotion data is real but easy to miss and dangerous to misread. This spotter scans anonymized HR records for patterns a person should look at.
sonnet1 weekHRIS exportpandasOpenAIConfluence
Claude
69ROI
73Scale
$1.4k89Saved
ROI for
README.md
Why this subagent
Bias in pay or promotion data is real but easy to miss and dangerous to misread. This spotter scans anonymized HR records for patterns a person should look at.
Every finding comes with its caveats: sample size, the limits of the data, and a clear note that this is a signal for human review, not a verdict. It helps an HR or legal team know where to look, without pretending the numbers prove intent.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Group records by role and level, then look for gaps that track protected attributes.
pending
Surface patterns worth a human review, always stated as signals, never conclusions.
pending
Produce a report with the caveats, sample sizes, and limits of each finding spelled out.
pending
Sample 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.