Skip to content
PromptifyLab

Business & Operations

HR & Hiring prompts

8 prompts Free · no sign-up Works in ChatGPT, Claude & Gemini Search & filter these

Job ads, screening questions, interview guides and feedback that says something. Below are 8 copy-ready prompts. Fill in the [BRACKETS], copy, and paste into ChatGPT, Claude, Gemini or any capable assistant.

Hiring is where generic AI output does the most damage: an invented-sounding job ad attracts the wrong people, and a bland rejection burns a candidate who might have been right next year.

The 8 prompts

Beginner 7 blanks to fill

Write a job description that filters correctly

Produce a JD that attracts the right people and deters the wrong ones.

Prompt
Write a job description.

ROLE: [JOB TITLE]
TEAM AND WHO THEY REPORT TO: [CONTEXT]
THE THREE THINGS THEY WILL ACTUALLY DO MOST DAYS: [LIST]
WHAT SUCCESS LOOKS LIKE AT 6 MONTHS: [OUTCOME]
HARD REQUIREMENTS: [NON-NEGOTIABLE SKILLS/CERTIFICATIONS]
NICE TO HAVE: [LIST]
WORK SETUP: [REMOTE/HYBRID/ONSITE, LOCATION, HOURS]
SALARY RANGE: [RANGE, or 'not disclosed']

Structure:
- Opening: two sentences on the actual problem this person solves. No company boilerplate.
- 'What you will do': 5-6 bullets, each starting with a verb, describing real work not responsibilities in the abstract
- 'What success looks like': the 6-month outcome, concretely
- 'You will probably be a fit if': 4-5 bullets describing experience, not years
- 'This is probably not for you if': 3 honest bullets - genuine downsides of the role
- Logistics: setup, location, salary, process steps and rough timeline

Rules:
- No 'rockstar', 'ninja', 'wear many hats', 'fast-paced environment', 'work hard play hard', 'like a family'
- Never state a years-of-experience number. Describe the experience instead.
- The 'not for you if' section must contain a real drawback, not a humblebrag.

What you get: A job description that reads like it was written by a human who has done the job, with an honest drawbacks section.

Tip: The 'not for you if' section raises application quality more than anything else in the post. Self-selection is cheaper than screening.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Intermediate 4 blanks to fill

Build a structured interview scorecard

Replace gut-feel interviews with something you can compare across candidates.

Prompt
Design a structured interview scorecard.

ROLE: [JOB TITLE]
THE FOUR COMPETENCIES THAT PREDICT SUCCESS: [LIST, or write 'suggest them' and infer from the role]
INTERVIEW LENGTH: [MINUTES]
INTERVIEWER'S LEVEL: [experienced hiring manager / first-time interviewer]

For each competency produce:
- A one-line definition of what good looks like in THIS role
- One primary behavioural question (past behaviour, not hypothetical)
- Two follow-up probes to use if the answer is vague
- A 1-4 rating scale where each level is described behaviourally. Level 1 and level 4 must be clearly distinguishable from a transcript.
- One 'red flag' answer pattern to watch for

Then produce:
- A time budget totalling the interview length, including 5 minutes for candidate questions
- An anti-bias note: for this specific role, name two things interviewers commonly mistake for competence

Rules:
- No hypothetical questions ('what would you do if'). Past behaviour only.
- Rating levels must describe observable behaviour, never 'strong' or 'weak'.
- Do not include culture-fit questions. Replace with a values-alignment question tied to a specific documented value if provided.

What you get: A four-competency scorecard with behavioural anchors, probes, red flags and a time budget.

Tip: Behaviourally anchored rating scales are the single highest-value part. 'Rate communication 1-5' produces noise; describing what a 2 sounds like produces signal.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Intermediate 6 blanks to fill

Write a performance review that is specific and fair

Turn scattered notes into a review that holds up.

Prompt
Draft a performance review.

EMPLOYEE ROLE: [ROLE]
REVIEW PERIOD: [DATES]
THEIR GOALS FOR THE PERIOD: [PASTE]
MY RAW NOTES AND EXAMPLES: [PASTE EVERYTHING, MESSY IS FINE]
OVERALL DIRECTION I WANT TO CONVEY: [exceeding / on track / needs improvement]

Produce:

1. SUMMARY - three sentences. States the overall direction plainly in the first sentence.

2. GOAL REVIEW - a table: Goal | Outcome | Evidence | Met/Partially/Not met. Evidence must come from my notes. Where I have given no evidence for a goal, write [NO EVIDENCE PROVIDED] rather than inventing any.

3. STRENGTHS - maximum three. Each needs a specific example from my notes and a sentence on the impact it had.

4. DEVELOPMENT AREAS - maximum two. For each: the observable behaviour (not a personality trait), the impact, and one concrete thing to do differently. Never write 'needs to be more confident' - describe what they did or did not do.

5. NEXT PERIOD - two or three goals, each with a measurable outcome.

Rules:
- Every claim needs evidence from my notes or a [NO EVIDENCE PROVIDED] flag
- No personality assessment. Behaviour only.
- Do not soften the overall direction. If it is 'needs improvement', sentence one must say so.
- Do not use the sandwich structure.

What you get: An evidence-linked review with unsupported claims flagged rather than invented, and a plainly stated overall direction.

Tip: The [NO EVIDENCE PROVIDED] flag turns the draft into a gap analysis of your own record-keeping. Those flags are the conversations you cannot defend.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Intermediate 2 blanks to fill

Screen a CV against a job description honestly

Get a structured read on a candidate without the model flattering the CV.

Prompt
Assess this CV against the job description. Be calibrated, not generous.

JOB DESCRIPTION:
"""
[PASTE JD]
"""

CV:
"""
[PASTE CV]
"""

Produce:

1. HARD REQUIREMENTS - a table: Requirement | Evidence in CV (quote it) | Met / Partially / Not evidenced. 'Not evidenced' is different from 'not met' - say which.

2. WHAT THEY HAVE ACTUALLY DONE - strip the CV's framing and describe the underlying work in plain terms. Where a bullet describes a team achievement, say so.

3. GAPS AND RISKS - including unexplained date gaps, very short tenures, and claims with no supporting detail.

4. THE THREE QUESTIONS to ask at screening that would most reduce uncertainty about this specific candidate.

5. RECOMMENDATION - Advance / Advance with reservations / Decline, one sentence of reasoning.

Rules:
- Do not infer skills from job titles.
- Do not reward CV polish. A well-written CV for a weak match is still a weak match.
- Ignore name, age, gender, nationality, photograph, university prestige and address entirely. If the CV contains them, do not reference them.

What you get: A requirement-by-requirement assessment with quoted evidence, de-framed experience, and three targeted screening questions.

Tip: Distinguishing 'not evidenced' from 'not met' is the important line. Most rejections at screening are actually 'the CV did not say', which is a question, not a no.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Advanced 6 blanks to fill

Prepare for a difficult employee conversation

Plan a conversation about performance or behaviour before you have it.

Prompt
Help me prepare for a difficult conversation with someone who reports to me.

THE ISSUE: [WHAT IS HAPPENING]
SPECIFIC INCIDENTS: [DATES AND WHAT HAPPENED - as factual as you can]
IMPACT: [ON THE TEAM, THE WORK, OR THEM]
WHAT I HAVE ALREADY TRIED: [PREVIOUS CONVERSATIONS OR SUPPORT]
OUTCOME I WANT: [WHAT CHANGES]
MY RELATIONSHIP WITH THEM: [CONTEXT]

Produce:

1. OPENING - exactly what to say in the first 30 seconds. Name the topic directly. No warm-up.
2. THE FACTS - my incidents restated as observable behaviour with impact, stripped of interpretation. Flag anything I have written as a judgement rather than an observation.
3. WHAT I MIGHT BE MISSING - three plausible explanations for this behaviour that I have not considered, including ones where the cause is me or the system.
4. QUESTIONS TO ASK - four, designed to let them explain rather than defend. Open, not leading.
5. WHAT GOOD LOOKS LIKE - the specific change, stated so both of us would know it when we see it.
6. IF IT GOES BADLY - responses for: they get upset, they disagree with the facts, they blame someone else, they say nothing.
7. WHAT I SHOULD NOT SAY - phrases to avoid in this specific conversation.

Do not write a script for the whole conversation. Prepare me, do not perform it for me.

What you get: A preparation brief with your judgements flagged, alternative explanations, and responses for the four ways it can go wrong.

Tip: Section 3 is the one that changes outcomes. Going in with one explanation of someone's behaviour is how these conversations fail.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Intermediate 4 blanks to fill

Turn an exit interview into something actionable

Extract patterns from departures instead of filing them.

Prompt
Analyse this exit interview.

ROLE AND TENURE: [ROLE, HOW LONG THEY STAYED]
STATED REASON FOR LEAVING: [WHAT THEY SAID]
EXIT INTERVIEW NOTES:
"""
[PASTE]
"""
PREVIOUS EXITS FROM THIS TEAM (if any): [BRIEF NOTES, or 'none']

Produce:

1. STATED VS LIKELY - what they said, and what the notes suggest. Be explicit that the second is inference and mark confidence as high/medium/low. People rarely give the real reason in an exit interview.

2. FIXABLE VS NOT - separate causes into: within this manager's control, within the company's control, and outside anyone's control (life events, better offer elsewhere, career change).

3. SIGNALS WE MISSED - what in the notes suggests this was visible before they resigned, and when.

4. PATTERN CHECK - against previous exits if provided. Say plainly if there is no pattern; do not manufacture one from a single data point.

5. ACTIONS - only for things in the fixable columns. Maximum three. Each with the role who owns it.

Do not recommend an engagement survey.

What you get: A separation of stated from likely cause, with confidence levels, missed signals and at most three owned actions.

Tip: Forcing the model to mark inference confidence stops a single exit interview becoming an organisational theory.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Intermediate 5 blanks to fill

Design a 30-60-90 day plan for a new hire

Give a new starter a structured ramp with checkpoints.

Prompt
Write a 30-60-90 day plan.

ROLE: [JOB TITLE]
SENIORITY: [LEVEL]
TEAM SITUATION: [e.g. replacing someone, new role, team in crisis, stable team]
THE PROBLEM THEY WERE HIRED TO SOLVE: [ONE SENTENCE]
KEY STAKEHOLDERS: [ROLES THEY MUST BUILD RELATIONSHIPS WITH]

For each of the three phases produce:
- The theme of the phase in four words
- LEARN: what they should understand by the end of it
- DO: concrete deliverables, with 'done when' criteria
- MEET: who, and the one question to ask each person
- MANAGER CHECKPOINT: the three questions the manager should ask at the end of the phase, and what a worrying answer sounds like

Calibration rules:
- Days 1-30: understanding and small reversible contributions only. No major changes.
- Days 31-60: first owned deliverable. One thing they own end to end.
- Days 61-90: a proposal or change that reflects their own judgement about the role.
- If the team situation is 'in crisis', compress this and say what you are trading off.

End with: the three earliest signals this hire is not working out, and by when you would see each.

What you get: A three-phase ramp plan with manager checkpoints and explicit early-warning signals.

Tip: The early-warning signals at the end are for the manager, not the hire. Write them down on day one, before you are invested in the decision.

Open in Written for Claude, ChatGPT, Gemini · Reviewed September 18, 2026
Beginner 9 blanks to fill

Write job offer and rejection messages candidates respect

Communicate hiring decisions clearly and kindly, including helpful feedback where appropriate.

Prompt
Write candidate messages for a hiring decision.

ROLE: [JOB TITLE]
STAGE REACHED: [application / first interview / final interview]
DECISION: [offer / rejection / on hold]
FOR OFFERS: salary and key terms [DETAILS], start date [DATE], response deadline [DATE], next steps [STEPS]
FOR REJECTIONS: whether I can share feedback [yes/no], and the main reason [REASON]
COMPANY TONE: [DESCRIBE]

Write:
1. The message for this decision
2. If rejection after interview: 2-3 lines of specific, useful feedback that are fair and cannot be read as discriminatory (focus on job-related evidence from the interview)
3. A short phone script if I call first
4. A template version with [PLACEHOLDERS] for reuse

Rules: no false promises ("we'll keep you on file" unless we really will), no vague reasons, and never reference age, gender, family, religion, nationality, health or any protected characteristic.

What you get: A clear offer or rejection message, fair job-related feedback, a phone script and a reusable template.

Tip: Candidates remember how they were rejected. Two lines of real, job-related feedback turn a rejection into a good impression of your company.

Open in Written for ChatGPT, Claude, Gemini · Reviewed September 25, 2026

Where AI actually helps here

  • Turning a real description of the work into a job ad that describes the job rather than the company’s self-image
  • Generating interview questions that probe a specific competency instead of testing interview technique
  • Drafting structured, defensible feedback from rough scoring notes

Where it falls down

  • Anything that touches a hiring decision. Assessment of a real candidate is a human judgement with legal weight
  • Screening CVs at scale — this is regulated in several jurisdictions and the bias risk is real
  • Writing a culture section. It will produce the same four sentences every company uses

The mistake almost everyone makes: Asking it to evaluate the person

Use AI on the artefacts — the ad, the question set, the scoring rubric, the structure of your feedback. Keep the judgement about a human being with humans. That is not only an ethics point: a model given a CV will produce a confident assessment with no basis, and it is very persuasive.

Free tool: Prompt Builder

Runs in your browser. No sign-up, nothing uploaded.

Open the Prompt Builder →

Questions people ask


Can AI screen CVs?

Technically yes. In several jurisdictions, including under the EU AI Act, automated screening of candidates carries specific obligations, and the bias research is not reassuring. Use it to structure your own review, not to replace it.


How do I make an AI-written job ad not sound AI-written?

Give it the real answer to “what will this person actually do in week one”, and forbid the vocabulary: no “fast-paced”, no “rockstar”, no “passionate about”. Most of what makes a job ad sound generated is that it was generic before anyone typed it.