Skip to content
Automation Squad
Hand to your teamWritten for ChatGPT

Build a hiring scorecard for a role I've never hired before

Robert MacKelfresh

By Robert MacKelfresh

Founder, Automation Squad

Off-the-shelf interview questions produce inconsistent scoring because interviewers interpret 'strong communicator' differently — the rubric anchors here fix that by forcing a shared definition of each score. It also builds the scorecard around the specific failure mode you're worried about, which a generic template can't do.

The prompt

I'm hiring for a role I have not hired for before and I don't fully trust my own instincts on what "good" looks like for it. Build me an interview scorecard.

Role: [paste job title and a rough description of what this person will actually do day to day — not the job posting, the real work]
Team they'll work with: [one line]
Biggest risk if we get this hire wrong: [one line — e.g. "they can talk a good game but can't execute," or "they're technically strong but can't influence without authority"]

Build:
1. Five must-have competencies, ranked, each with a one-line definition specific to this role (not generic "communication skills")
2. One interview question per competency designed to surface a real example, not a rehearsed answer — include what a strong vs. weak answer sounds like
3. A 1-4 scoring rubric per competency (1 = clear no, 4 = clear yes) with a one-line anchor for each score so two interviewers rate consistently
4. One red flag specific to the risk I named above, and the question most likely to surface it
5. A "reference check" question that tests something a candidate can't fake in an interview

Format as a table I can print and hand to interviewers. No generic competencies like "team player" — every item should trace back to what I said the role actually does.

Copy it, paste it, run it. Nothing here is gated.

Pairs with: Hiring Scorecard (printable)

The prompt does the thinking; this gives it somewhere to land. Not built yet — it ships with this prompt when it is.

More for the same job

Written for ChatGPT as of August 2026. Models change — if this stops working the way it should, that is worth telling us about.