HR & RECRUITING

Indeed Resume Rubric Scorer to Airtable Shortlist

Pulls each new Indeed applicant's resume, scores it against your role rubric with an LLM, and writes a ranked.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew applicant on tracked Indeed jobCustom MCP server
  • ActionFetch resume text and job details from IndeedCustom MCP server
  • ActionScore resume against role rubricOpenAI
  • LogicBucket score into Strong / Maybe / Pass
  • OutputWrite ranked row to Airtable shortlistAirtableAirtable

What it does

Every new applicant on a tracked Indeed job gets their resume scored against a structured rubric (required skills, years of experience, must-have certifications) and lands in an Airtable table sorted by fit score. Recruiters open one view and work the top of the list down instead of reading every resume cold.

When to use it

Use it for high-volume roles where 80% of applicants are clearly out of scope and a human reading every PDF is wasted time. Best when you have a stable rubric you can describe in a few bullet points per role.

How it works

  1. 1A new application on the watched Indeed job posting triggers the run.
  2. 2The flow fetches the applicant's parsed resume text and job details from Indeed.
  3. 3OpenAI scores the resume against the rubric, returning a 0-100 fit score, a one-line rationale, and any disqualifying gaps as structured JSON.
  4. 4A logic step buckets the score into Strong / Maybe / Pass tiers.
  5. 5The result is written to Airtable with the score, tier, rationale, and a link back to the Indeed profile, ready for the recruiter's ranked view.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Custom MCP serverConnect any MCP-compatible tool you own.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect AirtableBases, tables, views, automations.
  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.