HR & RECRUITING

Stale Internal Req Re-Match and Pipeline Refresh

On a schedule, it finds internal roles that have sat open too long with no qualified applicants, re-runs matching against the current tenured talent pool.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerTwice-weekly schedule starts sweep
  • LogicFlag reqs open past staleness threshold with no candidates
  • ActionPull current tenured eligible talent pool from AirtableAirtableAirtable
  • ActionRe-score pool against stale reqs with OpenAIOpenAI
  • ActionAppend newly qualified candidates to pipeline in AirtableAirtableAirtable
  • OutputSend recruiter a refreshed-reqs summary in SlackSlack

What it does

Keeps aging internal reqs from dying quietly. It detects roles open past a staleness threshold, re-runs the match against today's eligible employees (whose tenure and skills change over time), and hands recruiters a refreshed candidate list so the role keeps moving.

When to use it

Use it when internal roles linger for weeks because the first matching pass came up empty and nobody re-checks as new people become eligible. Good for high-volume internal pipelines.

How it works

  1. 1A schedule runs the sweep (e.g. twice weekly).
  2. 2It reads the open-roles table and flags reqs open past the staleness threshold with zero active internal candidates.
  3. 3For each stale req, it pulls the current tenured, eligible talent pool from the directory.
  4. 4An OpenAI call re-scores the pool against the req and returns any newly qualified candidates with rationale.
  5. 5New candidates are appended to the req's pipeline in Airtable.
  6. 6The owning recruiter gets a Slack summary of refreshed reqs and the new names to action.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect OpenAIModels, embeddings, files.
  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.