HR & RECRUITING

Agent-drafted comp adjustment briefs from band drift into Monday

An agent reviews each out-of-band employee, drafts a tenure- and performance-aware adjustment recommendation, and attaches it as a manager-ready brief on the Monday review item.

CategoryHR & Recruiting
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerMonthly schedule begins the run
  • ActionFetch out-of-band employees with tenure and performanceGoogle BigQueryBigQuery
  • LogicAgent reasons an adjustment toward refreshed midpoint
  • ActionFormat rationale into a manager briefOpenAI
  • OutputCreate Monday review item with brief for sign-offmonday.com

What it does

This workflow goes beyond flagging drift to drafting the recommendation. For every employee outside band, an agent pulls their tenure, level, and last performance signal, reasons about an appropriate adjustment toward the refreshed midpoint, and writes a short manager-ready brief that lands on a Monday review item.

When to use it

Use it when managers need context, not just a flag — a starting recommendation that accounts for where the person sits in the new band and their recent history. Best for orgs that want to accelerate comp conversations while keeping a human in the loop for approval.

How it works

  1. 1A monthly schedule begins the run.
  2. 2A BigQuery query returns out-of-band employees with tenure, level, and performance fields.
  3. 3The agent evaluates each case and drafts a proposed adjustment with rationale and a target inside the refreshed band.
  4. 4An OpenAI step formats the rationale into a concise brief.
  5. 5A Monday item is created with the brief in the update thread and the manager as owner for sign-off.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect monday.comVisual work management for teams.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.