HR & RECRUITING

Out-of-Band Offer Investigator (Agent + Slack)

An agent that, when an offer is flagged out-of-band, researches comparable internal pay and recent approved exceptions.

CategoryHR & Recruiting
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerOut-of-band offer eventHTTP webhook
  • ActionGather comparable salaries from BigQueryGoogle BigQueryBigQuery
  • LogicReview precedent and reason over a recommendation
  • ActionDraft recommendation with rationale
  • OutputPost recommendation to SlackSlack

What it does

When an offer breaches its band, this agent-driven workflow doesn't just flag it. It investigates: it gathers comparable salaries for the same level and location, reviews recent precedent for approved exceptions, weighs the candidate's stated rationale, and produces a written recommendation (approve, counter, or hold) with supporting reasoning. The recommendation is posted to Slack for the comp partner to action.

When to use it

Use it when out-of-band offers are common enough that a comp partner spends real time building the justification each time. The agent does the legwork and proposes a defensible decision, leaving the human to confirm.

How it works

  1. 1An out-of-band offer event triggers the agent.
  2. 2The agent queries comparable current salaries and bands from BigQuery for context.
  3. 3The agent reviews recent approved-exception precedent and the offer's rationale.
  4. 4It reasons over precedent, equity, and budget to draft a recommendation with rationale.
  5. 5The recommendation and evidence are posted to Slack for the comp partner to approve or override.

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 SlackChannels, DMs, threads, mentions.
  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.