HR & RECRUITING

Comp-Band Midpoint Outlier Sweep with Drafted Review Notes

After a market-data refresh lands in BigQuery, this sweep finds employees whose salary has drifted below their band midpoint, drafts a per-person review note.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMarket-data refresh lands in BigQueryGoogle BigQueryBigQuery
  • ActionQuery employees vs. band midpointGoogle BigQueryBigQuery
  • LogicFilter to below-midpoint outliers past threshold
  • ActionDraft per-person review note
  • OutputPost ranked outlier list to People Slack channelSlack

What it does

Whenever a fresh market-data table lands in BigQuery, this workflow recomputes each employee's position against their compensation band and surfaces anyone now sitting below the band midpoint. For each flagged person it drafts a short, neutral review note (current pay, midpoint, percent gap, suggested adjustment band) and posts a ranked summary to a private People-team Slack channel.

When to use it

Run it right after your quarterly or monthly market-data vendor refresh, when refreshed midpoints can silently push people out of position. Best for teams that already warehouse comp and headcount in BigQuery and want a repeatable outlier list instead of a manual spreadsheet pass.

How it works

  1. 1A scheduled BigQuery check detects the refreshed market-data table.
  2. 2A query joins active employees to their band and computes the gap to midpoint.
  3. 3A filter keeps only employees below midpoint beyond a tolerance threshold.
  4. 4For each match, a note is drafted with the gap math and a suggested band.
  5. 5The ranked outlier list plus draft notes is posted to the People Slack channel.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect SlackChannels, DMs, threads, mentions.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    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.