Audit intermediate Works with: Any AI

Interview Question Set Audit for Fairness

Table output Has example

Check questions for relevance and risk.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Rate this prompt

Loading ratings…

Audit the interview questions for a role. The question list and the job description: [QUESTIONS_AND_JD]. How answers are scored: [SCORING]. Panel members: [PANEL].

Check that each question links to a requirement, that questions are the same for all candidates, that none ask about protected characteristics or personal plans, that scoring anchors exist, and that follow-ups are planned. Flag questions that invite stereotype or luck.

Return a table with Question, Link to requirement, Risk (red, amber, green) and Rewrite, a scoring guide with anchors for a good, average and weak answer, and a panel briefing of ten lines. Employment law is [VERIFY] for [JURISDICTION] with an adviser.

Also suggest how to train panel members to take notes on evidence and not impressions, and a rule for resolving disagreements between scorers.

Then build the complete structured interview kit. For each competency, provide a main question, two follow-ups, what a strong answer includes, what a weak answer includes, and a scoring scale with anchors from 1 to 5. Add a candidate briefing note that explains the format and length, and a panel briefing covering how to take notes, how to avoid small talk that drifts into personal topics, and how to score independently before discussing. Provide a debrief agenda in which scores are shared first and discrepancies are discussed with evidence. Include a checklist for reasonable adjustments and how to offer them without asking invasive questions. Suggest a review of results after the round to see whether the scores predicted anything and whether any question produced unusual patterns. Employment and equality rules are [VERIFY] for [JURISDICTION] and should be confirmed with an HR adviser.

Offer a checklist and plain-language questions, not conclusions. If a point could change my legal position, say so, tag it [VERIFY], and tell me to check it with a qualified adviser in [JURISDICTION] first.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

See an example result (fictional data)
Question review (invented sales coordinator role)
Q2 "Do you plan to start a family?" Risk red. Remove; ask about availability for required hours instead.
Q4 "Describe a time you handled a difficult customer." Linked to requirement: customer communication. Keep; add anchors.
Q6 "Where are you from originally?" Risk red. Remove.
Q8 "Are you a culture fit?" Vague. Rewrite: "Tell us about a team you worked in and how you contributed."
Scoring guide (Q4): 1 blames customer; 3 describes steps; 5 gives action, result and learning.
Panel briefing: same questions, notes on evidence, score before discussing. Equality rules [VERIFY].

Illustrative only, made-up data. Your results will differ and must be reviewed.

Related prompts