HR & RECRUITING

Screen new Indeed applicants against a rubric into Airtable

Pulls new applicants for your matched Indeed jobs, scores each resume against a role-specific rubric with AI, and writes a ranked, decision-ready record to Airtable.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerEvery few hours, list applicants for matched Indeed jobs
  • ActionFetch each applicant's resume from Indeed
  • ActionScore resume against role rubric with OpenAIOpenAI
  • LogicDrop candidates below the minimum score
  • OutputWrite ranked record (score, verdict, notes) to AirtableAirtableAirtable

What it does

This workflow turns a noisy Indeed inbox into a clean, scored shortlist. On a schedule it fetches applicants for your active job postings, pulls each resume, scores it 0-100 against a rubric you define per role (must-have skills, years of experience, location fit), and lands the result in an Airtable base with a verdict of Advance, Maybe, or Reject plus the reasoning behind the score.

When to use it

Use it when a high-volume req is generating more applicants than a recruiter can read in a day, and you want every candidate scored consistently against the same bar instead of by whoever happens to open the email. Best for roles with clear, checkable requirements.

How it works

  1. 1A schedule fires every few hours and lists applicants for your matched Indeed jobs.
  2. 2For each new applicant the workflow fetches the full resume text from Indeed.
  3. 3An OpenAI step scores the resume against the role rubric and returns a number, a verdict, and a short rationale.
  4. 4A logic step drops anything below your minimum score so only viable candidates continue.
  5. 5Each surviving candidate is written to Airtable as a ranked record with score, verdict, and notes.

Set it up

What you configure once, before turning it on.

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