Get ahead: advanced moveSource-backedVerified 2026-04-20

Recruiter / HR Talent Acquisition Specialist / Screen applications and shortlist candidates by role fit

Bias-checked rubric + Claude API batch pipeline

For high-volume roles, run resumes through a Claude API workflow that applies a legal-reviewed rubric, masks protected-class signals, and outputs structured scores into a spreadsheet. A human recruiter reviews every shortlist.

Tool

Claude API + spreadsheet

Open tool

Best for

Analysis & Decisions

Typically under $0.05 per resume on Sonnet tier

Setup

3 hrs

One-time setup estimate

Workflow

1Collect the source material for "Screen applications and shortlist candidates by role fit" before opening the tool.
2Run the starter prompt in Claude API + spreadsheet and paste in the real context.
3Review the output for accuracy, tone, names, numbers, and policy-sensitive details.
4Save the improved prompt or checklist so the next run takes less time.

Inputs you need

- Recruiter / HR Talent Acquisition Specialist
- Screen applications and shortlist candidates by role fit
- Examples, notes, files, or customer context for this task
- Your preferred tone, constraints, and final format

Expected output

- Bias-checked rubric + Claude API batch pipeline
- A usable draft or workflow for screen applications and shortlist candidates by role fit
- A repeatable prompt you can improve after each run

Ready-to-copy asset

Starter prompt

You are scoring a single anonymized resume against a predefined rubric.

Inputs (already masked):
- Redacted resume text
- Job ID and role type
- Rubric (must / nice / red flag)

Return JSON only:
{
  "must_hits": [{"criterion": "...", "evidence": "..."}],
  "nice_hits": [{"criterion": "...", "evidence": "..."}],
  "red_flags": [{"criterion": "...", "evidence": "..."}],
  "fit_score": 0,
  "confidence": "low|medium|high",
  "reviewer_questions": ["..."]
}

Do not output a hire recommendation. If the input still contains name, age, nationality, or other protected attributes after masking, set fit_score to null and flag "masking-failure".

Caveats

- Do a human review before sending, publishing, filing, or making a decision.
- Verify numbers, names, claims, citations, and compliance-sensitive details.
- AI drafts. You decide. Final responsibility is yours.

Measurable value

7 min saved per run

Before: 8 min. After: 1 min.

Back to action plan Unlock more solutions