HR & Management

Verified against ChatGPT · 2026-08-11

Generate interview questions with the follow-up probes that catch a rehearsed answer

Writes a set of role-specific interview questions, each paired with two or three follow-up probes designed to surface real depth or expose a memorized answer, plus a flag on any question that risks drifting into illegal or discriminatory territory.

ChatGPT (GPT-5.1)4 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Write interview questions for the role and competencies below, for a single interview slot of a specific length. Every question needs follow-up probes attached, not just the headline question, because the headline question alone rarely distinguishes a candidate who lived the experience from one who prepared a polished story about it.

ROLE
Field Sales Manager, covering a 6-person regional team

COMPETENCIES TO PROBE IN THIS SLOT
Coaching a rep through a lost deal, managing a rep who's missing quota, and adapting a sales process across two very different regional markets.

INTERVIEW SLOT LENGTH
45 minutes including intro and candidate questions at the end

RED FLAGS THIS ROLE SPECIFICALLY CARES ABOUT
We've hired sales managers before who could talk a great game about coaching but had actually never run a real 1:1 skill-building session, just performance write-ups.

For each competency, write one primary behavioral question ("tell me about a time...") and then two or three follow-up probes that go after specifics a rehearsed answer usually skips: what exactly the candidate personally did versus what their team did, what the actual measurable outcome was, what they would do differently now, and what constraint or disagreement they had to navigate that a clean success story tends to omit. Order the questions so the total time fits the given slot length, allowing roughly 8-10 minutes per competency including probes, and note where to cut if the candidate's answer is already thorough and where to dig if it's noticeably vague. Where a role-specific red flag is given, include at least one question or probe designed to surface it directly rather than hoping it comes up incidentally.

COMPLIANCE CHECK
After the question list, review every question for topics that are illegal or inadvisable to ask in a hiring interview in most US jurisdictions (age, marital or family status, disability, religion, national origin, salary history where banned by local law) and flag any question that risks touching one of these, with a suggested rewrite that gets at the legitimate underlying concern without the risky framing. Do not silently omit the flag — even if you don't think a question crosses the line, if it is adjacent to one of these topics, say so explicitly so the interviewer can judge it themselves.

OUTPUT FORMAT
One section per competency (primary question, 2-3 probes, rough time allocation), followed by a Compliance Check section listing any flagged question, why, and the suggested rewrite.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

The mechanistic reason a headline behavioral question alone under-performs is well established in interviewing practice: a candidate who has done ten interviews for similar roles has almost certainly rehearsed a polished STAR-format answer to "tell me about a time you coached someone," so the differentiating signal lives in the follow-up, where an unrehearsed candidate either produces specific, consistent detail or starts contradicting themselves and hedging. Naming the specific probe categories — personal contribution versus team's, measurable outcome, what they'd change, the constraint a clean story tends to omit — gives the model a concrete template for manufacturing exactly the kind of probe that catches this, rather than generating generic "can you tell me more?" filler that a prepared candidate handles as easily as the original question. Building in the time-per-competency allocation matters practically because interviewers without an explicit budget tend to let the first question run long and then have to rush or skip the last competency entirely, silently turning a three-competency loop into a two-competency one without anyone noticing until the debrief has a gap. The compliance check is included as a mandatory, non-optional pass specifically because interview questions drift into legally risky territory gradually and innocuously — a manager asking about "availability for a demanding schedule" is often reaching for a legitimate concern about the role's hours but is one follow-up question away from effectively asking about caregiving responsibilities, which is exactly the kind of adjacent-but-not-explicit risk a single compliance pass is designed to catch before it reaches a real candidate.

What you get back

Coaching a rep through a lost deal — Primary: Tell me about a time you coached a rep after they lost a deal they were confident about. Probes: What specifically did you say to them versus what did they figure out on their own? What was different about their next deal? What would you do differently if you coached that same conversation again today? Compliance flag: none in this section. Time: ~9 minutes.

Verified against

ChatGPT GPT-5.1 · 2026-08-11

Changelog

  • 2026-08-11 Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
Write a job description that matches the actual hiring bar instead of a wish list nobody meetsTurns a hiring manager's notes into a job description built around a true must-have vs. nice-to-have split, so the posting attracts candidates who can actually clear the bar instead of scaring off good ones with an inflated requirements list.ChatGPT (GPT-5.1)2026-08-08Build a candidate scorecard that stops a 4-person panel from scoring the same interview four different waysGenerates a per-candidate scorecard tied to the specific competencies this role was actually interviewed for, so a hiring panel's individual scores are comparable instead of reflecting how generous or strict each interviewer happens to be.ChatGPT (GPT-5.1)2026-08-09Calibrate what a 1 through 4 actually means before four interviewers disagree about it in the debriefProduces the scoring rubric itself — the shared definition of what each competency and each score level means — that a hiring panel reviews together before interviews start, so scorecards filled out later are measuring the same thing.ChatGPT (GPT-5.1)2026-08-10Build a first-two-weeks onboarding plan that gets a remote hire to their first real contribution, not just a meetings calendarProduces a day-by-day onboarding schedule for a new hire's first two weeks, anchored to one concrete early contribution they'll make, instead of a generic checklist of orientation meetings that leaves the new hire unsure what they're actually supposed to be doing.ChatGPT (GPT-5.1)2026-08-12
All HR & Management prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY