Generate likely interview questions from a job description
Derive evidence-seeking questions from explicit responsibilities and requirements without claiming insider knowledge
6 min setupTested with:ChatGPTReviewed: 2026-08-28
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Generate likely interview questions grounded in the job description.
Complete dated posting and verified process details:
[job]
Verified candidate experience, skills, gaps, transitions, and difficult areas:
[candidate]
Stage, duration, panel roles, technical/case elements, locale, and preparation time:
[format]
Do not claim these are the employer's actual questions. Map explicit requirements and responsibilities to questions that elicit evidence about behavior, technical judgment, problem solving, stakeholders, communication, motivation, role understanding, constraints, and learning. Label each question's source, competency, likelihood rationale, what a strong answer must demonstrate, unsafe assumptions to avoid, and likely follow-ups. Include fair gap/transition questions without coaching deception. Prioritize a manageable core set, then optional questions. Return preparation evidence map, story reuse limits, questions the candidate should ask, and areas the posting cannot predict.
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Job description
Operations Analyst. Required: advanced Excel, two years operational data, clear writing. Responsibilities: weekly capacity reporting, service-variance investigation, depot-manager partnership, planning-process improvement, recommendations to Operations Director. Preferred: SQL, Power BI, logistics. Occasional depot visits. Interview details: first stage is a 45-minute panel; no technical test has been announced.
Candidate evidence
Retail supervisor since Sep 2023. Excel staffing workbook for 45 employees; investigated stock variances with three store managers; adopted checklist; weekly trading notes. No SQL, Power BI, logistics, depot work, or director presentation. Wants to move into analysis-focused work. Finds questions about weaknesses difficult.
Interview format
First-stage 45-minute UK panel. Panel roles unknown. Prepare over two evenings. Do not invent a technical exercise or exact employer questions.
Example output
Core practice set
“Walk us through an operational report you built and how you ensured it was reliable.” Source: weekly capacity reporting/Excel. Demonstrate inputs, formulas, validation, users, checks, limits; follow-up: what failed and what changed?
“Tell us about a variance you investigated when the cause was unclear.” Source: service-variance responsibility. Demonstrate definitions, evidence, stakeholder inquiry, alternative explanations, resolution; do not equate stock and service without explaining transfer.
“Describe a process improvement that colleagues initially resisted.” Source: planning improvement/partnership. Demonstrate listening, pilot, adaptation, adoption; preserve ownership.
“How have you communicated an analytical recommendation to a senior audience?” Source: director recommendations/writing. Candidate evidence is weaker; answer with the actual area-manager notes, name the boundary, and explain how you would adapt—not invent director delivery.
“What would you check before trusting a weekly capacity figure?” Technical judgment: grain, definitions, missing/duplicate rows, period, reconciliation, version, changes. Use actual practice only.
“You have not used SQL or Power BI; how would you close that gap?” Preferred-gap question. State current level honestly, transferable data concepts, concrete learning evidence if any; no false proficiency.
“Why move from retail supervision to this analyst role?” Use candidate-stated motivation plus evidence of already choosing analytical work.
Two evenings: map one distinct story to questions 1–3; do not reuse the workbook as every answer. Prepare honest gap response and one writing sample description. Candidate questions: metric definitions, source systems, first 90-day outputs, hybrid/depot pattern, and learning support. Unknown: actual panel emphasis and any later assessment.
Why this works
1
Requirement-to-question mapping produces role-specific practice without pretending to know a private interview script.
2
Evidence targets focus preparation on defensible examples rather than memorized ideal wording.
Check the result
Can every core question be traced to a job requirement, responsibility, or verified process detail?
Do prompts seek behavior and reasoning rather than keyword recitation?
Are candidate gaps handled truthfully without implying a fabricated answer?
ChatGPT