HR & RECRUITING

Agentic Below-Band Pay Equity Investigation

When a market-data refresh signals new midpoints, an agent investigates below-midpoint employees, cross-checks tenure, performance, and demographic-blind cohorts.

CategoryHR & Recruiting
Enginepaperclip
Difficultyadvanced
Triggerwebhook
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMarket-data refresh webhookHTTP webhook
  • ActionQuery below-midpoint cases with contextGoogle BigQueryBigQuery
  • LogicAgent reasons and classifies each case
  • ActionWrite review memo per case to NotionNotionNotion
  • OutputSlack summary of recommend-adjust casesSlack

What it does

Triggered by a market-data refresh webhook, an agent investigates each employee now sitting below their band midpoint. Rather than a flat threshold, it weighs tenure in role, recent performance rating, and how the person compares to a blinded peer cohort, then drafts a defensible review memo explaining whether the gap looks justified or warrants adjustment. Memos land in Notion and a summary goes to Slack.

When to use it

Use it when raw below-midpoint flags create too many false positives and you need judgment that accounts for context before escalating. Good for organizations that want an auditable, reasoned memo per case ahead of a comp committee.

How it works

  1. 1A market-data refresh webhook fires the investigation.
  2. 2The agent queries BigQuery for below-midpoint employees and their context fields.
  3. 3For each case it reasons over tenure, performance, and peer cohort.
  4. 4A decision step classifies each as justified, watch, or recommend-adjust.
  5. 5The agent writes a review memo to Notion per case.
  6. 6A Slack summary flags recommend-adjust cases to the comp committee.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect BigQueryDatasets, queries, schemas.
  3. 3
    Connect NotionPages, databases, comments.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.