WEEK 105 :: POST 2 :: CHATGPT
Directions Given To The A.I. This Week+
Instructions Given to each A.I. — Please provide 3 prompt variations that share this objective:
Each A.I. also received two static attachments: the blog post template (structure) and the authoring instructions (voice and standards). The text below is the week-specific assignment as sent — reflowed for the web; wording unchanged.
I'd like you to write this week's Ketelsen.ai post. Two files are attached: the blog post template (the structure to follow) and the authoring instructions (context, voice, and standards). Please read both before you begin, then produce the complete post in a single response.
This week's theme: "Interview Engineering — Preparing Like It's a Performance."
This is Week 6 of an eight-week series on running a job search with AI. The pipeline from Week 5 is producing interviews, and here the series' car-DNA shows again: this is test-drive week, and the test drive runs both directions. Most candidates rehearse answers to questions they hope will come. Few build a story inventory they can deploy against any question — and fewer still prepare to evaluate the employer while being evaluated, which is the half of the interview the reader controls completely.
The signature move of this post is the reverse test drive: diagnostic questions that force a company to reveal its true condition. Why is this role open? What happened to the last person in it? How does the team decide what to build next? What does success look like at ninety days, and who decides? A company's answers — and its flinches — tell the reader more than three hours of its careers page.
The deliverable the reader should walk away holding: a story bank built from their real record, mock-interview transcripts with pressure applied, and a diagnostic question list for reading the employer's true condition.
THE SERIES CONTRACT — identical every week; it binds every prompt you design. This series' tagline is its editorial contract: "Use AI like an analyst, not a ghostwriter." It is written for a reader in a market unsettled by AI itself — some readers are searching precisely because AI eliminated their last role. Write with that reader at the table: no AI-efficiency cheerleading, no automation jokes, no promises that AI will "do it for you" anywhere a human hiring decision is involved. And hold one line in every prompt: the AI is the reader's private analyst, coach, and sparring partner — it structures, researches, rehearses, and questions. It does not ghostwrite. Anything a hiring human will read or hear — résumé lines, cover letters, outreach messages, interview answers, negotiation emails, resignation letters — must end in the reader's own words and be true. Prompts should drive toward drafts the reader rewrites and owns, and should say so explicitly. Employers increasingly restrict how AI may be used in their own hiring decisions for legal and compliance reasons, and recruiters increasingly recognize — and discard — material that reads machine-written. A prompt that makes a reader look AI-generated hurts them twice. Posts that ignore this contract should expect to lose the week. Two practical notes. First: a standing “About this series” notice covering these same points is added to every published post automatically at publication — acknowledge the frame in your own voice where your week's prompt calls for it, but do not write a formal disclaimer block of your own, and do not open every post with the same acknowledgment paragraph: outside the weeks whose prompts explicitly carry the series frame, this contract lives in your tone and your prompt design. Second, the framing is POSITIVE: used this way — analyst backstage, reader on the page — AI is an advantage no hiring human will ever hold against your reader. Write like that is true, because it is.
The three prompts should help a reader:
- Predict the questions. From one real job description, generate the likely interview agenda — the screens, the behavioral probes, the technical areas, the "walk me through your résumé" landmines specific to this reader's history — so preparation is targeted instead of general.
- Build the story bank and rehearse under pressure. Turn Week 3's achievement inventory into structured stories (situation, action, result), then run the AI as a mock interviewer that asks follow-ups, challenges vague answers, and does not let "we" hide what the reader did — with honest feedback after each round.
- Assemble the interview intelligence package. For one real interview: research questions about the interviewers' backgrounds the reader fills in, company-specific talking points from the Week 4 dossier, the diagnostic questions to ask, and the red flags to watch for in how the process itself is run — lateness, vagueness, goalpost movement.
At the advanced tier, the strongest version of this week is the full bidirectional package — offense and defense in one preparation system: story bank tuned to this posting, mock transcripts with the hard follow-ups already survived, and a diagnostic layer that treats the interview as the reader's due-diligence session too. That structure is worth reaching for.
A constraint for this week. AI models cannot see a specific company's actual interview process, panel composition, or question bank. No prompt may ask the AI to state what a named company's interview process actually is, or what questions it actually asks, as fact. The prompts should generate likely shapes from the job description and role type, and point the reader to where real process reports live (interview-review sections of employer-review sites, people who have interviewed there) to confirm. And the mock-interview prompts coach honesty: the AI sharpens how the reader tells true stories; it does not script embellishments. One bright line belongs in the post itself: preparation is the AI's whole territory — the live interview is not. No prompt, tip, or aside may suggest real-time or covert AI assistance during an actual interview — an earpiece feed, a second screen whispering answers. It is the interview equivalent of the ghostwritten résumé, it is increasingly named in employer policy, and a candidate caught performing someone else's answers loses more than the round. Rehearse with the AI until the answers are genuinely the reader's; then walk in alone.
Design the prompts so the AI does what it is genuinely good at: pattern prediction from a document, structured drill with adaptive follow-up, and turning a real record into deployable narrative. The reader supplies the posting, their true stories, and what they find about the company; the AI supplies the pressure, the structure, and the questions worth asking back.
Series dependency chain, for the Metadata block: Week 6 consumes Week 3's achievement inventory (the story bank's raw material), Week 4's dossier (company-specific talking points and red-flag context), and Week 5's pipeline (the interviews themselves). Week 6 produces the story bank, mock transcripts, and diagnostic question list — consumed by Week 7 (what the reader learned in interviews becomes negotiation context) and Week 8 (the diagnostic reads feed the final decision).
Because readers may arrive at this post with an interview on Friday and none of the earlier artifacts, the prompts should work from a job description and a memory of their own career, while making clear the preparation is stronger with a real story inventory behind it.
Three difficulty tiers as always — Beginner, Intermediate, Advanced — each a genuinely different approach to the same problem, not the same prompt at three lengths.
On examples: this is a career topic that touches every industry. The template lists tech startup / retail / freelance as suggested industry examples — those are marked MAY, and adapting them is expected here. A first panel interview after years away from interviewing, a behavioral round where every story keeps coming out as "we," and an onsite where the reader suspects the team is quietly on fire are the right kinds of contexts. Choosing them over the suggested business examples is correct behaviour and will not be scored against you.
A note on supplied figures. Anything marked `[SUPPLIED — use as given]` above came from Ketelsen.ai's own research brief. Use it freely — you are not fabricating by repeating it, and you will not be marked down for leaving it uncited. Do not attach an invented source to it. (No supplied figures this week.)
## BEFORE YOU SUBMIT — STRUCTURAL CHECK
(This block is identical every week. It exists because these specific items are the ones posts drop, and a dropped structural item costs compliance points for something that takes one minute to add.)
Your post is parsed by a script before any human reads it. Confirm all seven:
1. ☐ Response begins with `PLATFORM: <your name>` and `WEEK: 6` 2. ☐ `## Lead` present once, at the very top, before Variation 1 3. ☐ `## In one line` present in all three variations 4. ☐ `## What this prompt gives you` present in all three variations 5. ☐ `## The Prompt` present in all three variations, with the prompt in double quotes beneath it 6. ☐ `## Introductory Hook` and `## Current Use` present in all three variations (three of each — not one) 7. ☐ Every template heading written as `##`, none bolded instead; prompt breakdown is running text split on ` : `, with no `###` headings inside it
A complete post has 57 `##` headings. If your count is well short, a section is missing or was bolded instead of hashed.
One extra check this week: confirm no prompt asks the AI to state a named company's actual interview process or questions as fact, and the mock-interview prompts coach truthful storytelling — sharper delivery of real stories, never scripted embellishment. Also confirm nothing anywhere in the post suggests live or covert AI assistance during an actual interview (the series contract's bright line for this week).
About this series. AI is reshaping work — for some readers, it's part of why you're searching at all. We don't pretend otherwise. And the hiring world is wary of AI-written material: many employers restrict how AI may be used in their own hiring decisions, and recruiters increasingly recognize — and discard — machine-written applications. So this series teaches a different approach: use AI as your private research analyst, interview coach, and thinking partner, while every word an employer sees or hears from you stays genuinely, verifiably yours. AI behind the scenes. You on the page.
An interview is not a memory test; it is a live performance built from evidence, rehearsal, and judgment. This week gives you three prompts at three depths: a fast agenda predictor, a pressure-testing story coach, and a full bidirectional interview intelligence system that helps you prepare your answers while diagnosing the employer. Use the one that matches the interview in front of you, then walk into the room with stories you own and questions the company cannot answer with slogans.
The Interview Agenda Predictor
Turn one job description into a focused interview preparation map.
Most interview anxiety comes from preparing for everything and feeling ready for nothing. A job description already contains clues about what the employer is likely to test: repeated responsibilities, unusually specific requirements, leadership expectations, technical tools, and problems hidden inside phrases such as “fast-paced” or “cross-functional.” This prompt teaches the AI to read those clues as an analyst, not pretend it has access to the company’s private question bank. In a few minutes, you get a practical agenda for what to rehearse, what evidence to gather, and where your background may invite follow-up questions.
Why this matters now
Hiring processes vary widely, and generic lists of “top interview questions” rarely tell you which questions deserve tonight’s preparation time. A role-specific forecast is more useful because it connects each likely question to language in the posting and to proof from your own history. The result is not a script. It is a preparation map that helps you spend less time memorizing polished sentences and more time recovering true examples you can explain naturally.
Act as my private interview-preparation analyst, not my ghostwriter. I will paste a real job description and a short, truthful summary of my background.
Analyze the posting and produce a likely interview agenda. Do not claim to know this company’s actual process, panel, or question bank. Label every prediction as an inference from the role description, and tell me what I should verify through public interview reviews or people who have interviewed there.
Give me: 1. The 10 most likely interview questions, grouped as opening, behavioral, role-specific, and risk or gap questions. 2. For each question, the exact clue in the job description that made it likely. 3. The proof I should prepare from my real experience: a result, decision, conflict, failure, lesson, or technical example. 4. The three questions most likely to expose a weak or unclear part of my background. 5. Five diagnostic questions I can ask the employer to learn why the role is open, what success means in the first 90 days, how decisions are made, and what obstacles the team is facing. 6. A 30-minute preparation plan ordered by priority.
Do not write interview answers for me. Ask me to supply the facts, help me organize them, and remind me to restate everything in my own words. Preparation is your territory; the live interview is mine.
Job description: [PASTE HERE]
My truthful career summary: [PASTE HERE]
How the AI reads this prompt
Practical examples from different industries
A hospital operations manager has not interviewed in nine years and is preparing for a panel interview. She pastes the posting and a brief career summary showing staffing, patient-flow, and compliance work. The prompt predicts questions about handling competing priorities, influencing physicians without direct authority, and measuring operational improvement. It also flags a likely gap question about her limited experience with a newly listed analytics platform. Her output becomes a 30-minute plan: recover one patient-flow story, one conflict story, one compliance decision, and one honest explanation of how she learns unfamiliar systems.
A manufacturing supervisor is pursuing a continuous-improvement role after spending most of his career on the production floor. The prompt notices repeated language about root-cause analysis, safety culture, and cross-shift coordination. It generates likely questions tied to those phrases and asks him to prepare proof involving a defect investigation, a safety intervention, and a disagreement between operations and maintenance. The value is not prediction theater; it is focus. He stops rehearsing generic leadership answers and starts gathering the three examples most likely to prove he can translate floor experience into improvement work.
A recent computer science graduate is interviewing for an entry-level security analyst position. Her résumé is light on paid experience but includes a capstone, a home lab, and volunteer help-desk work. The prompt identifies likely questions about incident triage, learning unfamiliar tools, communicating technical findings, and working with incomplete information. It also predicts a risk question about the difference between lab practice and production responsibility. That warning lets her prepare a truthful answer that distinguishes what she has done from what she is ready to learn, rather than overstating experience she does not have.
Creative use case ideas
- Use the prompt before an internal promotion interview to identify questions about leadership scope, peer relationships, and the shift from doing the work to directing it. - Run it for a volunteer board interview, fellowship, or competitive academic program where the “job description” is a mission statement and selection criteria. - Paste two similar job descriptions and compare the predicted agendas to learn how the same title changes across organizations. - Use the risk-question section to prepare for a career gap, industry change, return from caregiving, or move from self-employment into a larger organization. - Give the output to a trusted friend and ask them to choose five questions for an offline practice round.
Adaptability tips
Change the number of predicted questions to match your time. Ask for five when the interview is tomorrow morning, or twenty when you have a full week and several rounds ahead.
Replace the career-summary field with your résumé when you want the AI to identify likely “walk me through your résumé” transitions, but remove personal information you do not need to share.
For a technical role, add: “Separate conceptual questions, troubleshooting scenarios, and hands-on exercises.” For a leadership role, add: “Prioritize decisions involving people, resources, ambiguity, and accountability.”
For an internal role, add the known interview format and names of the functions represented, but ask the AI to analyze only the information you provide rather than inventing private details.
After the first interview, paste your notes and ask the AI to revise the likely agenda for the next round based on what was actually emphasized.
Pro tips
- Ask the AI to score each predicted question on likelihood, importance, and preparation risk. Prepare first for questions that are both likely and costly to answer poorly. - Add a “disconfirming evidence” line: require the AI to explain why each prediction might be wrong. This keeps plausible guesses from hardening into certainty. - Request a one-page output after the full analysis so you have both the reasoning and a compact rehearsal sheet.
Prerequisites
Have the complete job description and a truthful summary of your background ready. A current résumé helps, but it is not required. You should also know the date and likely format of the interview so the preparation plan can be realistic. If you have Week 3’s achievement inventory, use it; if not, a list of several projects, decisions, problems, and results is enough to begin.
Required tools
Any general-purpose AI assistant that accepts long text prompts and can analyze a pasted job description. A free tier is usually sufficient for one posting and a short career summary, although longer context windows are helpful when pasting a résumé and detailed job description together. A notes document is optional for saving the preparation map.
Frequently asked questions
Is the AI predicting the company’s real interview questions?
No. It is identifying likely themes from the posting, role type, and background you provide. Treat the result like a weather forecast for preparation: useful for deciding what to carry, not proof of exactly what will happen. Confirm company-specific process details through public interview reviews, recruiter information, or people who have interviewed there.
What if the questions feel generic?
The usual cause is thin source material. Paste the full posting, include a more specific career summary, and ask the AI to quote the clue behind every question. If a question cannot be tied to the posting or your history, tell the model to remove it and replace it with one that can.
Can I use the generated answers word for word?
This prompt intentionally does not generate answers. It identifies the evidence you should recover and organize, because you must be able to explain every claim naturally and survive follow-up questions. Use the AI to find missing facts and improve structure, then speak in language that sounds like you.
What should I do if the posting is vague?
Ask the AI to separate what can be inferred from what must be verified. Then use your recruiter screen to ask about the team’s priorities, the reason the role is open, the first major deliverable, and how the interview process is structured. A vague posting is not a reason to invent certainty; it is a reason to prepare better questions.
Recommended follow-up prompts
- Achievement Inventory Builder from Week 3: Recover measurable projects, decisions, conflicts, failures, and lessons before turning them into interview stories. - Employer Dossier Builder from Week 4: Assemble verified company context, strategic pressures, and questions that deserve human confirmation. - Story Bank Pressure Drill: Use Variation 2 below to turn the predicted agenda into live rehearsal with follow-up questions.
Tags and categories
Tags:
interview preparation, job description analysis, likely interview questions, behavioral interviews, career gaps, employer questions, job search
Categories:
Job Search, Prompting Fundamentals
Citations
NOT APPLICABLE
The Story Bank Pressure Drill
Build true stories, then rehearse until vague answers stop surviving.
A strong interview answer is rarely invented in the moment. It is retrieved from a prepared bank of real situations, then adapted to the question without sounding memorized. The trouble is that most candidates store their experience as job duties, not as stories about decisions, tradeoffs, mistakes, conflict, and results. This prompt turns your achievement inventory into a compact story bank and then changes roles: it becomes a skeptical interviewer that asks one question at a time, follows the weak spots, and refuses to let “we” conceal what you personally did. You keep the facts and the voice; the AI supplies structure and pressure.
Why this matters now
Behavioral interviews reward specificity, but specificity is difficult when stress shortens memory and the interviewer keeps probing. A candidate who has prepared only one perfect version of a story can collapse when asked what changed, who disagreed, what failed, or what they would do differently. This prompt creates adaptable evidence rather than brittle scripts. It also produces a transcript of where the answer became vague, defensive, overlong, or unsupported, giving the reader something concrete to improve before the real conversation.
Act as my private interview coach and sparring partner. You may organize, question, and critique my true experience, but you may not invent facts, inflate results, or write a final answer for me to memorize. Anything I say to an employer must remain true and end in my own words.
I will provide:
- A job description.
- My achievement inventory, project notes, or a rough list of real experiences.
- Any gaps, transitions, or topics I am worried about.
Run this in four phases.
PHASE 1 — BUILD THE STORY BANK Identify six high-value story categories for this role, such as achievement, conflict, failure, leadership, ambiguity, customer impact, technical judgment, or learning. Match my real experiences to those categories. For each story, create a compact fact sheet with: situation, stakes, my specific responsibility, actions I personally took, result, evidence, lesson, and questions the story could answer. Mark missing facts as QUESTIONS FOR ME. Do not fill them in.
PHASE 2 — FIND COVERAGE GAPS Compare the story bank with the job description. Show which likely competencies have strong proof, weak proof, or no proof. Ask me targeted questions to recover additional real examples before rehearsal begins.
PHASE 3 — PRESSURE INTERVIEW Interview me one question at a time. Do not show the full question list in advance. After each answer, ask one or two realistic follow-ups based on what I actually said. Challenge vague language, unsupported claims, excessive context, and answers that hide behind we. Ask what I did, why I chose it, what changed, how I know, and what I learned. Do not help me during the answer.
PHASE 4 — COACHING REVIEW After each completed question sequence, give feedback under: credibility, relevance, specificity, ownership, structure, and natural delivery. Quote short phrases from my answer that weakened it. Then ask me to answer again in my own words. Do not supply a polished replacement answer unless I explicitly ask for a rough outline, and label any outline as material I must rewrite and own.
Maintain a running transcript with the original question, my answer, follow-ups, my revised answer, and the coaching notes. At the end, give me the three stories that need more evidence and the three habits most likely to hurt me.
Do not claim to know this company’s actual interview questions. Infer likely competencies from the job description and label them as inferences. This AI session is for preparation only. No live or covert assistance during the real interview.
Job description: [PASTE HERE]
My real experience notes: [PASTE HERE]
My concerns: [PASTE HERE]
How the AI reads this prompt
Practical examples from different industries
A cybersecurity incident responder is interviewing for a senior role, but every practice answer begins with “we investigated,” “we contained,” and “we decided.” The prompt converts his real incident notes into stories about triage, escalation, stakeholder conflict, and post-incident improvement. During rehearsal, the AI interrupts the pattern with follow-ups: What did you personally notice? Which decision was yours? What did you recommend when others disagreed? The transcript shows that his experience is strong, but his ownership is invisible. His revised answers become clearer without exaggerating the team’s work.
A retail district manager is pursuing an operations director position. Her achievement inventory includes store turnarounds, hiring improvements, and a difficult closure, but the stories are scattered across spreadsheets and memory. The prompt organizes them into six fact sheets, then detects weak evidence for strategic planning and executive communication. During the pressure round, it challenges a long answer that spends two minutes describing the background before reaching her decision. She rehearses a second version that keeps the context but brings the stakes, action, and measurable result forward.
A graduate student is preparing for a competitive research fellowship interview. His experience is real but does not fit conventional corporate achievement language, so he keeps minimizing it. The prompt builds stories around research ambiguity, collaboration, failed experiments, ethical judgment, and communication to non-specialists. The mock interviewer probes a project that did not produce the expected result and asks how he changed his method. The coaching review helps him explain the quality of his reasoning without pretending the failed result was secretly a success.
Creative use case ideas
- Use the pressure drill to prepare for a promotion conversation where colleagues already know the background and will notice inflated storytelling immediately. - Practice a career-gap explanation until it is direct, truthful, and proportionate rather than apologetic or evasive. - Adapt the rubric for graduate admissions, grant panels, residency interviews, or oral examinations. - Ask a friend or mentor to review the transcript and mark places where the revised answer still does not sound like you. - Use voice transcription for one practice round so the AI critiques spoken habits such as rambling openings, filler words, and buried conclusions.
Adaptability tips
Change the six story categories to match the role. A technical position may need troubleshooting, system design, incident response, and tradeoff stories; a people-leadership role may need coaching, delegation, conflict, performance management, and organizational change.
Adjust the interviewer style. Ask for a warm recruiter screen, a skeptical hiring manager, a rapid-fire panel, or an executive who keeps returning to business impact. The point is not theatrical imitation of a real person; it is exposure to different pressure patterns.
Add a time limit such as 90 seconds for first answers and 30 seconds for follow-ups. This helps readers who know their material but lose structure when they speak too long.
For a first interview after a long break, begin with supportive coaching and increase pressure over three rounds. For an experienced candidate, start with the strict rubric immediately.
After each real interview, add the questions you were actually asked and rerun the coverage audit. Your story bank should become more accurate as the search progresses.
Pro tips
- Tell the AI to distinguish a missing fact from a weakly expressed fact. The first requires more evidence; the second requires better delivery. - Add a “counterfactual probe” after strong stories: ask what might have happened if the candidate had chosen differently. This reveals judgment rather than rehearsed chronology. - Require the coach to track repeated habits across rounds, not just critique each answer in isolation. - Run the final rehearsal without feedback until the end. Continuous coaching is useful for learning, but delayed feedback better tests whether the improvements hold.
Prerequisites
Bring the job description and at least five truthful experience notes. Week 3’s achievement inventory is ideal, but a rough list of projects, conflicts, mistakes, results, and lessons will work. Set aside enough uninterrupted time to answer aloud or in writing. Decide whether you want a supportive, neutral, or demanding interviewer before you begin.
Required tools
A conversational AI assistant that can maintain context across multiple turns is required. Voice mode or speech-to-text is helpful but optional; written rehearsal still exposes structure and evidence gaps. Use a notes application or document to save the story bank and transcript if the AI platform does not preserve long sessions reliably.
Frequently asked questions
What if I do not have an achievement inventory?
Start with rough memories rather than waiting for perfect preparation. List projects, difficult decisions, mistakes, conflicts, customer problems, times you learned quickly, and results you can support. The prompt will identify missing facts, but it should never manufacture them for you.
Should I answer aloud or type my responses?
Speaking is better for testing timing, retrieval, and natural delivery, while typing is better for seeing structure and missing evidence. A strong sequence is to type the first round, speak the second, and compare where your spoken answer loses detail or becomes longer. Use whichever mode you can practice consistently.
What if the AI is too nice?
Increase the evaluation standard explicitly. Ask it to act like a skeptical but fair interviewer, require evidence for every criticism, and tell it not to praise an answer unless it meets the rubric. You can also ask it to identify the strongest reason a hiring manager might remain unconvinced.
Is it okay to use a polished outline from the AI?
An outline can help if every fact came from you and you rewrite the language. Do not memorize a model-generated paragraph and call that preparation; follow-up questions will quickly reveal whether the wording is yours. The goal is fluent ownership of real evidence, not perfect recitation.
How many stories do I need?
Six flexible stories are often more useful than twenty brittle scripts because one strong story can answer several competencies when you understand its facts. Coverage matters more than the count. Use the gap analysis to decide whether your bank contains enough proof for this particular role.
Recommended follow-up prompts
- Interview Agenda Predictor: Use Variation 1 to identify the competencies and risk questions the story bank must cover. - Interview Intelligence Package: Use Variation 3 to add company due diligence, diagnostic questions, process red flags, and a post-interview debrief. - Week 7 Negotiation Context Builder: Convert what you learn about scope, urgency, constraints, and success measures into evidence for offer evaluation and negotiation.
Tags and categories
Tags:
mock interview, behavioral interview, story bank, STAR method, interview coaching, truthful storytelling, adaptive follow-up, career preparation
Categories:
Job Search, Applied Prompting
Citations
NOT APPLICABLE
The Bidirectional Interview Intelligence System
Prepare your case while conducting due diligence on theirs.
An advanced interview is two investigations happening at once. The employer is testing whether your evidence supports the role; you are testing whether the role, team, mandate, and operating conditions support the promises. Candidates often prepare the first investigation and improvise the second, which is how they leave with warm impressions but little decision-grade information. This prompt builds a bidirectional system: predicted agenda, evidence matrix, story bank, pressure transcript, interviewer research questions, reverse-test-drive diagnostics, process red flags, and a post-interview debrief. It does not pretend the AI knows private company facts. It turns what you know, infer, and still need to verify into one controlled preparation package.
Why this matters now
Senior, specialized, and high-stakes interviews rarely fail because a candidate forgot the standard questions. They fail when evidence does not match the role, a follow-up exposes a weak claim, or the candidate never tests whether the opportunity is coherent. The same process can also hide risk through vagueness, shifting expectations, unexplained turnover, or inconsistent descriptions of success. A structured package helps the reader enter with a case, a set of verification targets, and a disciplined way to interpret what happens without converting every awkward moment into a verdict.
Build a complete bidirectional interview intelligence package for one real opportunity. Act as my private analyst, coach, red-team reviewer, and debrief facilitator. Do not ghostwrite statements for me to recite. Do not invent career facts, company facts, interviewer facts, or private interview-process details. Anything a hiring human reads or hears must be true, rewritten in my own words, and fully defensible under follow-up.
INPUTS I WILL PROVIDE A. The full job description. B. My résumé or career summary. C. My achievement inventory or raw project notes. D. My company dossier, including sources and uncertainties, if available. E. Public information I found about the interviewers, if available. F. Known interview format, date, and participants supplied by the recruiter. G. My constraints, concerns, and decision criteria.
Use three evidence labels throughout:
- KNOWN: directly supported by material I supplied.
- INFERRED: a reasonable interpretation from the role or evidence.
- VERIFY: important but not established.
Produce the package in eight modules.
MODULE 1 — ROLE THESIS Summarize the job’s apparent mission, the business problems it may exist to solve, the capabilities most likely to be tested, and the hidden tensions suggested by the posting. Quote the posting evidence behind each conclusion. Do not present inference as company fact.
MODULE 2 — INTERVIEW AGENDA MODEL Map likely interview stages and question families from the role type and information I provide. For every predicted area, include confidence, supporting clues, what evidence I need, and how to verify the real process through the recruiter, public interview-review sections, or people who have interviewed there. Never state a named company’s actual process unless I supplied a verified source.
MODULE 3 — EVIDENCE-TO-REQUIREMENT MATRIX Match every major requirement to my strongest real evidence. Rate each match as strong, partial, weak, or missing. For partial or weak matches, identify the honest bridge I can explain and the question I should expect. Do not conceal gaps with transferable-skills language unless the underlying evidence supports it.
MODULE 4 — DEPLOYABLE STORY BANK Build eight concise story records from my real history. Each record must include: trigger questions, situation, stakes, my decision, actions I personally took, tradeoffs, result, evidence, lesson, what I would change, and unresolved facts to ask me. Optimize stories for flexible recall, not memorized prose.
MODULE 5 — ADVERSARIAL REHEARSAL Run a mock interview one question at a time. Vary the style across recruiter, hiring manager, peer, executive, and skeptical follow-up. Do not reveal future questions. Probe vague claims, missing numbers, unclear ownership, contradictions, and overrehearsed language. After each sequence, score relevance, evidence, ownership, judgment, clarity, and authenticity from 1 to 5, explain the score, and require a second answer in my own words.
MODULE 6 — REVERSE TEST DRIVE Create diagnostic questions in five categories: why the role is open, what success means at 30/60/90 days, how priorities and decisions are made, what resources and constraints shape the work, and what happened to the previous person or previous attempts. For each question, include what a clear answer might reveal, what an evasive answer might reveal, and one neutral follow-up. Do not treat hesitation alone as proof of a problem.
MODULE 7 — PROCESS SIGNAL WATCHLIST Create a watchlist for the interview process itself: scheduling reliability, interviewer preparation, consistency of role descriptions, respect for candidate time, clarity of evaluation, goalpost movement, and willingness to answer reasonable questions. Separate observations from interpretations. Give at least two benign explanations and two concerning explanations for ambiguous signals before drawing a conclusion.
MODULE 8 — INTERVIEW-DAY BRIEF AND DEBRIEF Produce a one-page brief containing my role thesis, five proof points, four stories to keep accessible, five diagnostic questions, and three verification targets. Then create a post-interview debrief form that captures questions asked, evidence used, new facts, unresolved claims, process signals, energy level, concerns, and follow-ups. End with a decision update: stronger interest, weaker interest, or unchanged, with reasons and confidence.
WORKFLOW RULES 1. Begin by auditing my inputs and asking only the highest-value missing questions. 2. Do not generate all eight modules until the minimum evidence is present. 3. Keep a provenance ledger showing which input supports each important conclusion. 4. When evidence conflicts, show the conflict instead of resolving it silently. 5. Challenge flattering interpretations as aggressively as negative ones. 6. Preparation ends before the live interview. Do not suggest real-time, covert, or second-screen AI assistance. 7. At the end, ask me to export the story bank, transcript, diagnostic list, and debrief into my own notes.
Start by listing the inputs you received, the inputs missing, and the five questions whose answers would most improve the package.
[PASTE INPUTS A-G HERE]
How the AI reads this prompt
Practical examples from different industries
A product leader is preparing for an onsite at a growing software company. The job description combines strategy, hands-on delivery, executive communication, and “building process in ambiguity,” while recruiter notes suggest the role has changed twice. The system labels the role’s mandate as INFERRED, maps her evidence to each requirement, and identifies one weak area: managing a product organization larger than her previous team. The reverse test drive gives her neutral questions about decision rights, prior attempts, and first-quarter success. The debrief later records that three interviewers described different priorities, a conflict worth verifying rather than instantly condemning.
A nonprofit operations director is interviewing for an executive role after a leadership transition. He provides the posting, audited accomplishments, public board materials, and his decision criteria around mission alignment and governance. The package builds stories about budget tradeoffs, staff trust, crisis response, and board communication, then red-teams a claim that initially sounds stronger than the evidence supports. Diagnostic questions explore why the role is open, how authority is divided between the executive director and board, and what resources support the stated goals. The output helps him prepare a candid case while evaluating whether the mandate is executable.
A skilled-trades training manager is considering a regional role that would require travel and responsibility for several underperforming sites. Her résumé proves instructor development and safety improvement but contains limited multi-site ownership. The evidence matrix marks that requirement partial rather than pretending it is solved. Rehearsal probes how her existing work transfers, while the reverse test drive asks how regional priorities are set, why the sites are underperforming, and what authority the role has to change staffing or curriculum. Her post-interview debrief captures the travel reality, decision rights, and whether the promised resources were confirmed.
Creative use case ideas
- Use the system for a final-round internal promotion where public company research matters less than conflicting stakeholder expectations and political constraints. - Adapt the reverse test drive for choosing a graduate advisor, residency program, board appointment, creative collaboration, or major volunteer commitment. - Run two opportunities through the same evidence and decision criteria so differences in fit are visible instead of buried in separate notes. - Use the provenance ledger after a disappointing interview to distinguish actual evidence from self-critical assumptions made under stress. - Revisit the debrief before Week 7 negotiation so the offer discussion reflects what the company revealed about urgency, scope, risk, and success.
Adaptability tips
Remove modules when the interview stage does not justify the full system. A recruiter screen may need only the role thesis, agenda model, four proof points, and five diagnostic questions. A final round may justify all eight modules.
Change the evidence labels when working in a regulated or technical field. For example, use VERIFIED, REPORTED, INFERRED, and UNKNOWN when source quality matters more than whether the information came directly from your notes.
Add role-specific rubrics. A security leadership role may score incident judgment, risk communication, and executive influence; a design role may score problem framing, critique response, and portfolio evidence.
Use the same debrief form after every interview in the pipeline. Consistent fields make it easier to compare roles and detect repeated process signals without relying on mood.
For panel interviews, create a participant map using only confirmed names, roles, and public information you provide. Ask the AI to generate questions you should research, not invented personal details or assumptions about what each person will ask.
Export each module into separate notes if the context becomes too large. Keep the provenance ledger and stable input set at the top so later sessions can continue without re-deriving the package.
Pro tips
- Add a confidence threshold: any conclusion below the threshold must appear only in the VERIFY list, not the interview-day brief. - Ask for a “narrative collision check” that finds contradictions between stories, résumé dates, scope claims, and the role thesis before an interviewer does. - Run a hostile and a charitable interpretation of the same process signals, then write the evidence that would distinguish them. - After the interview, lock the raw notes before asking the AI to summarize them. Preserving the original observation layer reduces hindsight rewriting.
Prerequisites
You need the complete job description, a current résumé or career summary, and several truthful examples from your work. The system is strongest with Week 3’s achievement inventory, Week 4’s sourced company dossier, and the confirmed interview details produced by Week 5’s pipeline. You should also define your own decision criteria, including role scope, manager quality, compensation needs, location, travel, stability, growth, and values. Public interviewer information is optional and must be supplied by you rather than invented by the model.
Required tools
A general-purpose AI assistant with a large context window and reliable multi-turn conversation is recommended. A document or knowledge-management tool is useful for storing the input set, provenance ledger, story records, transcripts, and debriefs. Web research tools are optional and should be used to gather public evidence; the reader must still verify company-specific claims and preserve source links in the dossier.
Frequently asked questions
Is this too much preparation for one interview?
It can be, which is why the system is modular. Use the full package for high-value, senior, unfamiliar, or final-round opportunities where the decision cost is high. For an early screen, run only the modules that change what you will do next.
How do I stop the AI from overinterpreting company red flags?
Preserve raw observations, require multiple explanations for ambiguous signals, and ask what evidence would distinguish them. A late interviewer may indicate disrespect, an emergency, or a calendar failure; the event matters, but the interpretation is not automatic. Use patterns and corroboration rather than a single awkward moment.
Can the system research the interviewers for me?
It can analyze public information you provide or retrieve through a tool you intentionally use, but it should not invent biographies, motives, or likely questions. Focus on professional background, published work, role responsibilities, and topics worth understanding. Keep the research respectful and relevant to the interview.
What if my evidence-to-requirement matrix has several weak matches?
Treat that as useful information, not a prompt failure. Decide which gaps can be bridged honestly through adjacent experience, which require a learning plan, and which may signal that the role is not a fit. The system should help you explain reality clearly, not manufacture symmetry between your background and the posting.
Should I bring the AI-generated brief into the interview?
Use the brief to prepare beforehand, then reduce it to ordinary notes permitted by the interview format, if any. Do not use the AI live, covertly, or through a second-screen answer feed. Rehearse until the ideas are yours, then enter the interview without hidden assistance.
Recommended follow-up prompts
- Week 7 Offer and Negotiation Context Builder: Convert verified scope, urgency, success measures, and interview signals into a negotiation plan grounded in the actual opportunity. - Week 8 Decision Review: Compare offers and opportunities using the same decision criteria, interview evidence, unresolved risks, and confidence labels. - Continuity Handoff Prompt: Compress the package into decisions made, verified facts, open questions, and next actions so a later AI session can continue without rebuilding the analysis.
Tags and categories
Tags:
interview intelligence, reverse interview, employer due diligence, evidence matrix, advanced prompting, mock interview, red-team review, interview debrief, provenance, job search system
Categories:
Job Search, Advanced Prompt Systems
Citations
NOT APPLICABLE
Which of the three should you use?
The Beginner prompt is the fastest route from uncertainty to focus. It treats the job description as a clue set and produces a prioritized agenda: likely questions, the evidence behind each prediction, the weak spots worth preparing, and diagnostic questions for the employer. Choose it when the interview is close, the source material is limited, or you need a strong result without building a larger system.
The Intermediate prompt changes the mode from analysis to performance. It builds a reusable bank of true stories, finds coverage gaps, then applies adaptive pressure one question at a time. Choose it when you know what the role may test but your answers remain vague, overlong, overly collective, or fragile under follow-up. The Advanced prompt combines both directions of the interview into one evidence-controlled package. It is best when the role is important enough to justify deeper preparation and when evaluating the employer is as consequential as presenting your own case.
All three prompts share the same operating principle: the AI stays backstage. It predicts patterns, organizes evidence, applies pressure, records uncertainty, and helps the reader ask better questions. It does not know a company’s private process, invent missing career facts, write a synthetic personality, or join the live interview. Start with the lightest prompt that solves the real problem, then move deeper only when the additional structure will change preparation or the decision.
TAGS:
