HR & RECRUITING

Match internal candidates the moment a req opens

When a new requisition is created in Notion, parses its required skills and ranks current employees from a BigQuery skills warehouse.

CategoryHR & Recruiting
EngineSim + Paperclip
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew requisition created in NotionNotionNotion
  • ActionExtract required skills and level from reqOpenAI
  • ActionPull active employee skill profilesGoogle BigQueryBigQuery
  • ActionScore and rank employees against the reqOpenAI
  • LogicKeep candidates above match threshold
  • OutputPost internal shortlist to hiring managerSlack

What it does

The instant a hiring manager files a new open req, this workflow surfaces the best-fit people already on payroll. It reads the requisition's required skills, level, and location, scores every active employee against them, and delivers a ranked shortlist with match reasoning to the hiring manager — closing the loop before anyone writes a job ad.

When to use it

Run this when your goal is internal-first hiring and reqs live in Notion. It is ideal for orgs that want to reduce time-to-fill and external recruiting spend by always checking the bench first.

How it works

  1. 1A new requisition page is created in the Notion reqs database (trigger).
  2. 2An OpenAI step extracts structured requirements — skills, seniority, function, location — from the req body.
  3. 3A BigQuery query pulls active employees with their skill profiles, tenure, and current role.
  4. 4An OpenAI scoring step ranks each employee against the req and writes a fit score plus a one-line rationale.
  5. 5A logic filter keeps only candidates above the match threshold.
  6. 6The ranked shortlist is posted to the hiring manager's Slack with apply-or-skip actions.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect NotionPages, databases, comments.
  2. 2
    Connect BigQueryDatasets, queries, schemas.
  3. 3
    Connect OpenAIModels, embeddings, files.
  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.