Rebuild the Résumé Against the Spec, Not in a Vacuum
WEEK 102 :: 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: "Getting Your Assets Right Before You Apply."
This is Week 3 of an eight-week series on running a job search with AI. The reader now has a target-role spec sheet from Week 2. This week they build the materials — résumé, LinkedIn presence, and positioning story — against that spec, not in a vacuum. The car-series parallel is "getting your money right before you shop": unglamorous preparation that determines how every later conversation goes.
This is also the series' myth-busting week. The reader has heard that an ATS robot rejects résumés for using the wrong font, that white-text keyword stuffing works, that six seconds is all any human ever spends reading. Some of this folklore contains a grain of truth; much of it is confidently wrong. The honest version — screening software filters and searches, recruiters scan before they read, tailoring beats tricks — is more useful than the folklore, and the prompts should be built on the honest version. What the prompts must not do is have the AI assert how any specific screening product behaves today as settled fact.
The deliverable the reader should walk away holding: a master résumé built against their target spec, a mined inventory of quantified achievements, and a positioning narrative that LinkedIn, cover letters, and interview answers all draw from.
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:
- Rewrite the résumé against a real job description. Take one actual posting for the target role and restructure the reader's résumé against it — matching the language the posting actually uses, surfacing the relevant experience, cutting what does not serve — with the reader supplying both documents.
- Mine achievements they forgot they had. The AI as a structured interviewer that digs quantified accomplishments out of the reader's work history — the project that saved a quarter of the budget, the process that cut a week to a day — because the raw material for every asset is specifics, and most people cannot list their own.
- Build the full asset system. The master résumé that tailored variants are cut from, a LinkedIn profile aligned to the same positioning, and a keyword strategy grounded in the language of real postings for the target role — one coherent story told at three surfaces, ready for Week 5's application engine.
At the advanced tier, the strongest version of this week is a master résumé plus tailoring engine — a system where the reader maintains one complete document and generates posting-specific variants on demand, rather than owning seventeen slightly different résumés. That structure is worth reaching for, and it sets up Week 5 directly.
A constraint for this week. Screening systems differ, change, and do not publish their rules. No prompt may ask the AI to state how a specific ATS product ranks or rejects candidates today, or to guarantee that a formatting choice will pass or fail screening. The prompts should build assets on durable principles — clear structure, the posting's own language, quantified specifics — and where the reader wants to verify a claim about screening, point them to named sources (the employer's own application guidance, recruiters in the target industry) rather than asserting it. And one line matters doubly here: everything in the résumé stays true. The AI structures and sharpens what the reader actually did; it does not invent metrics, titles, or dates, and a prompt that lets it should expect to be marked down.
Design the prompts so the AI does what it is genuinely good at: structured interviewing, restructuring documents against a target, translating accomplishments into the market's language. The reader supplies their history and their real numbers; the AI supplies structure, language, and the questions that surface what the reader forgot. And build the last step into the prompts themselves: the final pass belongs to the reader. A résumé line the reader cannot say out loud in an interview, in their own voice, is not theirs yet — and generic AI phrasing on a résumé is exactly what recruiters have learned to spot and discount. Every prompt that produces candidate-facing text should end by handing the draft back for the reader's own rewrite, and should say why that step is not optional.
Series dependency chain, for the Metadata block: Week 3 consumes Week 2's target-role spec sheet (the assets are built against it). Week 3 produces the master résumé, the achievement inventory, and the positioning narrative — consumed by Week 5 (the application engine cuts tailored variants from the master), Week 6 (the story bank is built from the achievement inventory), and Week 7 (the positioning narrative carries into negotiation).
Because readers may arrive at this post without having read the earlier weeks, the prompts should work for someone with any résumé and a role in mind, while making clear the assets come out sharper when they are built against a real Week 2 spec.
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 project manager translating operations work into product language, a laid-off analyst quantifying five years of "just doing my job," and a designer building a portfolio narrative 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 — including the folklore numbers: if a "six-second scan" or a "75 percent of résumés rejected" figure is reaching for your keyboard, write the sentence without it.)
## 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: 3` 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 how a specific screening product behaves as fact, or to guarantee a résumé will pass screening — and confirm nothing in any prompt invites the AI to invent achievements, metrics, titles, or dates that are not the reader's own. Also confirm every prompt that produces candidate-facing text ends with the reader rewriting and owning the final words (the series contract's final-pass rule).
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.
A résumé built in isolation usually becomes a polished history lesson: accurate, respectable, and only loosely connected to the job someone is trying to win. This week’s three prompts fix that from different directions—first by aligning one résumé to one real posting, then by interviewing you for achievements you have forgotten, and finally by turning those facts into a reusable résumé, LinkedIn, and positioning system. The goal is not to let AI impersonate you. It is to use AI backstage as an analyst so the final materials are focused, truthful, and unmistakably yours.
The Job-Description Relevance Pass
Turn one real posting into a focused résumé revision plan.
Most résumés are not terrible. They are simply trying to serve too many possible jobs at once. A hiring team looking for a project coordinator should not have to decode why your general administrative experience matters, just as a product-operations recruiter should not have to translate your internal company terminology. This prompt gives the AI one résumé and one real job description, then asks it to identify what deserves more attention, what should move, and what can be shortened. It replaces résumé folklore with a more durable question: does the document make the relevant evidence easy to find?
Why this matters now
Job seekers now encounter a noisy mix of advice about screening systems, keyword tricks, ideal fonts, hidden text, and supposedly universal recruiter behavior. Screening tools and hiring processes differ, so no prompt can honestly guarantee that a résumé will pass every system. What you can control is whether the document uses clear language, reflects the role’s actual priorities, and supports every claim with something you really did. This prompt creates that practical first pass without asking the AI to invent qualifications or imitate a résumé-writing machine.
Act as a careful résumé analyst and career coach, not a ghostwriter.
I will give you two documents:
1. My current résumé.
2. One real job description for a role I may apply to.
Compare them using only the information I provide. Do not invent achievements, metrics, dates, job titles, technologies, certifications, responsibilities, or experience. Do not claim that any formatting or keyword choice will guarantee success with an applicant-screening system.
Complete these steps:
1. Summarize the five most important capabilities the employer appears to want. Use plain language and distinguish required qualifications from preferences when the posting does.
2. Identify the strongest evidence already present in my résumé for each capability. Quote or reference the relevant résumé content.
3. Identify important capabilities that are missing, buried, vague, or described using different terminology.
4. Recommend what to move higher, expand, shorten, combine, or remove. Explain each recommendation.
5. Draft revised versions of up to six résumé lines using only facts already supported by my résumé. Match the job description’s language when it is accurate, but do not copy phrases that misrepresent my experience.
6. When a stronger line would require a fact I have not supplied, write a question or a visible placeholder such as [ADD REAL RESULT] instead of guessing.
7. Finish with a prioritized ten-minute editing checklist.
After producing the draft, remind me to rewrite every candidate-facing sentence in my own voice. Flag any line that sounds generic, inflated, or difficult to explain naturally in an interview.
Here is my résumé:
[PASTE RÉSUMÉ]
Here is the job description:
[PASTE JOB DESCRIPTION]
How the AI reads this prompt
Practical examples from different industries
Operations analyst returning to the market:
A laid-off analyst pastes a five-year résumé and a business-operations posting that emphasizes forecasting, cross-functional reporting, executive communication, and process improvement. The prompt finds that the résumé contains relevant work, but most of it is buried under internal project names. The expected output moves two forecasting examples upward, translates company-specific terminology into language supported by the posting, and asks for the real time or cost impact of three projects. This matters because the analyst does not need a fictional reinvention; the résumé needs a clearer line of sight between existing work and the employer’s priorities.
School-district project manager targeting product operations:
The candidate’s résumé describes scheduling, vendor coordination, policy implementation, and stakeholder meetings, while the desired role uses terms such as operational readiness, process documentation, launch coordination, and cross-functional alignment. The prompt should identify legitimate conceptual overlap without pretending the candidate has worked in software product development. Its revised lines might clarify scale, deadlines, stakeholder groups, and operational outcomes while leaving unsupported product terminology out. The value is disciplined translation: the reader can show transferable experience without disguising where it came from.
Community volunteer coordinator re-entering paid employment:
A caregiver has recent volunteer experience organizing food drives, managing schedules, recruiting helpers, and coordinating local partners, but the résumé treats the work as a small footnote. When paired with a nonprofit program-coordinator posting, the prompt should surface that evidence, ask for real participation numbers, and recommend whether the experience belongs in a more prominent section. The expected output does not inflate volunteering into a corporate title. It helps the reader describe genuine coordination work in a way that a hiring team can recognize.
Creative use case ideas
- Compare a résumé with a fellowship, apprenticeship, or returnship description rather than a conventional job posting. - Help a military veteran translate service terminology into accurate civilian language while preserving rank, scope, and context. - Review a teenager’s first résumé against a summer-job posting without inventing professional experience. - Compare a community-board biography with the responsibilities of a volunteer leadership role. - Use the same relevance pass on a portfolio introduction, speaker biography, or professional-association profile.
Adaptability tips
For a faster review, ask the AI to analyze only the résumé summary and the most recent two positions. For a career change, add a request to separate direct evidence, transferable evidence, and unsupported gaps so the model does not blur them together. If the job description is unusually long, ask for a first-stage role map before any résumé editing.
The prompt also works when the résumé cannot be uploaded as a file. Paste the text in sections and tell the AI not to begin until you write DOCUMENTS COMPLETE. When privacy matters, replace names, client identities, account numbers, internal system names, and confidential project details with neutral labels before submitting the material.
Pro tips
- Ask for a change log showing the original line, proposed line, evidence used, and reason for the change. - Request two revisions for each line: one conservative version and one more concise version. - After editing, start a new conversation and ask the AI to evaluate the revised résumé without showing it the earlier recommendations. This reduces the chance that it merely agrees with its own work. - Read every revised line aloud. If it feels unnatural or requires a long explanation, rewrite it.
Prerequisites
You need a current résumé and one complete, real job description. A Week 2 target-role spec sheet will make the analysis sharper, but it is not required. You should also know which facts are confidential and remove or generalize them before using a public AI service.
Set aside enough time to verify every proposed revision against your own records. The prompt can identify where a number would help, but you must supply the number or leave it out.
Required tools
Any general-purpose AI assistant that can accept pasted text is sufficient. File-upload support is convenient but not required. You will also need a word processor or plain-text editor for reviewing and applying changes.
A paid AI tier is not necessary for a normal-length résumé and posting, although limits vary by service. Review the privacy and data-use settings of the service before submitting personal or confidential information.
Frequently asked questions
Will this make my résumé pass an ATS?
No prompt can honestly guarantee that outcome. Employers use different screening products, configurations, workflows, searches, and human review practices, and those processes can change. This prompt focuses on the part you can defend: clear organization, accurate use of the posting’s language, relevant evidence, and truthful specifics. Treat claims about a particular employer’s screening process as something to verify through that employer’s own application guidance or knowledgeable recruiters in the field.
Should I paste every keyword from the posting into my résumé?
No. A term belongs in the résumé only when it accurately describes your experience, skills, credentials, or results. Copying unsupported language can create a misleading document and leave you unable to explain the claim during an interview. The better question is whether you have genuine evidence for the capability and whether your current wording makes that evidence easy to recognize.
What should I do when the AI recommends a metric I do not have?
Do not invent one and do not accept an estimate merely because it sounds realistic. Look for records, reports, calendars, project documents, performance reviews, or people who can help you reconstruct the result accurately. When no defensible number exists, use concrete nonnumeric evidence such as scope, frequency, complexity, audience, deadline, or observable operational change.
Can I use the AI’s revised lines exactly as written?
You should treat them as working drafts. Rewrite them in words you would naturally use, then confirm that every claim is true and that you can explain the context without relying on the AI’s phrasing. A strong résumé line should survive the interview question, “Tell me exactly what happened.”
Recommended follow-up prompts
- Evidence Checker: “For every sentence in this revised résumé, identify the exact source fact that supports it and flag anything inferred, ambiguous, or unsupported.” - Human-Voice Pass: “Interview me about how I naturally describe this work, then help me rewrite the selected lines without changing their factual meaning.” - Application Decision Review: “Compare my verified qualifications with the posting and separate strong matches, plausible transferable matches, learnable gaps, and true disqualifiers.”
Tags and categories
Tags:
résumé tailoring, job description analysis, career change, truthful AI use, job search preparation, résumé editing
Categories:
Career Development, Practical Prompting
Citations
- Assignment basis for using one real posting to restructure a truthful résumé: - Assignment constraint against product-specific screening claims and invented candidate facts: - External citations: NOT APPLICABLE.
The Achievement Excavation Interview
Turn forgotten work into a verified inventory of specific achievements.
People rarely forget the projects they worked on. They forget the details that make those projects valuable to someone outside the organization. “Managed reporting” may conceal a broken monthly process rebuilt into a one-day workflow. “Helped with onboarding” may mean designing the checklist used for every new employee across three locations. This prompt does not begin by writing résumé bullets. It interviews the reader one question at a time, follows promising details, separates facts from assumptions, and builds an inventory that can later support résumés, LinkedIn sections, cover letters, portfolios, and interview stories.
Why this matters now
AI is particularly useful when the problem is not a lack of experience but a lack of retrieval. A structured interviewer can keep asking about scale, difficulty, decisions, stakeholders, constraints, and outcomes until ordinary work becomes concrete enough to evaluate. That is more useful than telling the model to “make my accomplishments sound impressive,” which rewards decorative language before the underlying facts are known. The reader remains the source of truth; the AI supplies the questioning structure and organizes the answers.
Act as an achievement-mining interviewer and evidence organizer. Your job is to help me recover specific, truthful examples from my work history. Do not ghostwrite my résumé before you understand the facts.
I will provide my current résumé, a target role or target-role spec sheet, and any notes I have. Interview me one question at a time. Do not send a long questionnaire all at once.
Use this process:
1. Create a private interview plan covering my major roles, projects, recurring responsibilities, emergencies, improvements, leadership moments, difficult constraints, and recognition.
2. Begin with the experience most relevant to my target role.
3. Ask focused follow-up questions about the situation, problem, my personal actions, collaborators, scale, time frame, tools, decisions, and result.
4. When I give a vague answer such as ‘made it faster’ or ‘worked with several teams,’ ask for evidence. Help me search my memory using practical cues such as calendars, reports, ticket counts, budgets, deadlines, before-and-after steps, team size, frequency, customer volume, or feedback.
5. Never invent or estimate a number for me. Clearly label any uncertain detail as [VERIFY].
6. Distinguish what I personally did from what the team or organization accomplished.
7. Continue until we have at least eight useful achievement records, or until I tell you to stop.
For each completed achievement, create an evidence record containing:
- Achievement ID
- Target capability demonstrated
- Situation or problem
- My specific actions
- Scale and constraints
- Verified result
- Evidence source or verification method
- Confidence level: verified, remembered but unverified, or incomplete
- Missing follow-up questions
- Possible uses: résumé, LinkedIn, portfolio, cover letter, or interview story
After the interview, group the records by capability and identify the strongest evidence for my target role. Then draft two concise résumé-bullet options for the verified achievements only. Use visible placeholders for missing facts.
Do not add inflated adjectives or generic claims such as ‘results-driven.’ End by asking me to rewrite the candidate-facing drafts in my own voice and confirm that I can explain every line accurately in an interview.
Here is my target role or spec sheet:
[PASTE TARGET ROLE]
Here is my current résumé or work-history outline:
[PASTE RÉSUMÉ OR NOTES]
How the AI reads this prompt
Practical examples from different industries
Cybersecurity incident responder:
A responder remembers handling investigations, improving procedures, and mentoring analysts but initially describes the period as “doing normal incident-response work.” The AI interviews him about incident volume, severity, handoff delays, evidence preservation, coordination, documentation, and after-action improvements. It may uncover a verified example in which he redesigned an escalation checklist, reduced missing intake information, and shortened the time analysts spent requesting basic details. The output records the result only if the reader can verify it, distinguishes individual work from team outcomes, and identifies separate uses for a résumé bullet and an interview story.
Regional retail manager:
A manager says she “helped stores improve inventory,” which is too vague to evaluate. The interviewer asks how discrepancies were found, how many locations were involved, what process changed, who approved it, how often counts occurred, and where the results were recorded. The expected output might become an evidence record describing a new reconciliation routine across six stores, supported by audit reports and documented shrinkage changes. If the exact financial impact cannot be confirmed, the record retains operational evidence and marks the missing number for verification rather than manufacturing one.
Independent graphic designer building a portfolio narrative:
A designer has years of client work but remembers projects mainly by visual style. The prompt asks about the original business problem, audience, constraints, rejected directions, research, design decisions, production challenges, client adoption, and measurable or observable outcomes. The resulting inventory connects creative choices to evidence: a packaging system that simplified a product line, an identity system adopted across multiple locations, or a template library that reduced inconsistent production. This helps the designer write case studies grounded in decisions and results instead of relying only on attractive images.
Creative use case ideas
- Interview a retiring employee to capture institutional knowledge and overlooked contributions before departure. - Help a parent returning from caregiving reconstruct volunteer leadership, continuing education, and complex personal projects without disguising them as paid employment. - Mine examples for a graduate-school statement, scholarship application, teaching portfolio, or professional certification. - Build a story bank for an annual performance review before memories disappear into another year of routine work. - Interview a community organizer about an event, fundraiser, or neighborhood initiative and turn the answers into an accurate impact archive.
Adaptability tips
Change the interview lanes to match the target field. A designer may need questions about audience, constraints, alternatives, and critique; a salesperson may need territory, pipeline, deal cycle, objections, and revenue attribution; a technical professional may need system scale, reliability, risk, complexity, and incident impact. Keep the evidence, confidence, and ownership fields even when the domain changes.
For a shorter session, request three achievement records from the most recent role. For deeper work, run separate interviews for each position and merge the records afterward. When the conversation becomes long, ask the AI to produce a checkpoint summary containing completed IDs, unresolved questions, and the next interview topic so the work can continue without losing state.
Pro tips
- Ask the AI to challenge each achievement with the questions a skeptical interviewer might ask.
- Add a
minimum defensible claimfield showing the strongest statement supported even if an uncertain metric is removed. - Store supporting evidence locations—such as a report name or review date—without pasting confidential documents into the conversation. - Separate prevented problems from visible gains. Risk reduction, error prevention, and reliability improvements are legitimate achievements when described with evidence.
Prerequisites
Bring a résumé, work-history outline, performance reviews, project lists, or any notes that can help orient the interview. A target-role spec sheet is strongly recommended because it tells the AI which experiences deserve priority. You do not need complete metrics before starting; discovering what must be verified is part of the process.
Decide how you will protect confidential information. Use generalized client labels, remove personal data, and avoid sharing sensitive incident details, unreleased product information, protected records, or proprietary financial figures with a public AI service.
Required tools
Use a conversational AI assistant capable of maintaining a multi-turn interview. A spreadsheet, notes application, or document editor is useful for saving the final achievement records. Voice dictation can help readers who recall experiences more easily by speaking than typing.
No specialized résumé software is required. For a long career history, an AI service with a larger conversation limit may be more convenient, but the process can be divided by role on any general-purpose service.
Frequently asked questions
What if I cannot remember exact numbers?
Start with what you can verify and identify where a number might exist. Ask yourself whether the scale can be described through team size, locations, frequency, duration, customer group, project complexity, deadline, or before-and-after steps. A specific nonnumeric fact is better than a fabricated percentage. Leave the record marked incomplete until the uncertain detail is confirmed or deliberately removed.
Are team accomplishments acceptable on a résumé?
Yes, when your contribution is described accurately. State the team or organizational outcome, then make your role in producing it clear through your actions, decisions, ownership, or specialized contribution. Avoid language that implies you alone created an outcome delivered by many people. The interview process is designed to separate shared results from individual evidence without erasing collaboration.
How do I know whether an achievement is strong enough to keep?
A useful achievement usually demonstrates a capability relevant to the target role and contains enough context to understand what changed. It does not always require a dramatic financial result. Improvements in reliability, quality, speed, risk, access, coordination, customer experience, clarity, or decision-making may be valuable when they are specific and defensible. Keep weaker records in the inventory; they may support LinkedIn or interviews even if they do not make the résumé.
Will the interview take too long?
It can be divided into short sessions. Complete two or three records, save a checkpoint summary, and resume with the next role later. The process is intentionally slower than asking for instant résumé bullets because the raw material is more important than the first draft. Once the inventory exists, it can support multiple applications and interview rounds.
Recommended follow-up prompts
- Verification Planner: “Review these achievement records and create the quickest realistic plan for verifying every item marked remembered, incomplete, or uncertain.” - Story Builder: “Turn one verified achievement record into an interview-story outline with context, decisions, actions, result, lesson, and likely follow-up questions.” - Capability Coverage Audit: “Compare my achievement inventory with my target-role spec and show which required capabilities have strong, weak, or missing evidence.”
Tags and categories
Tags:
achievement inventory, quantified accomplishments, structured interviewing, career storytelling, evidence verification, résumé bullets, interview preparation
Categories:
Career Development, AI-Assisted Analysis
Citations
- Assignment basis for using structured interviewing to recover quantified accomplishments: - Assignment basis for keeping the reader as the source of facts and owner of final wording: - External citations: NOT APPLICABLE.
The Master Asset System and Tailoring Engine
Build one verified source system for every application asset.
Seventeen résumés become seventeen opportunities for drift. A metric changes in one version but not another. A strong project disappears from the document used for the best-fitting role. LinkedIn tells one story, the résumé tells a second, and the interview introduces a third. The advanced solution is not a more elaborate one-off rewrite. It is a source-of-truth system: verified facts, a market-language map, a complete master résumé, a positioning narrative, and a repeatable method for cutting a truthful role-specific version from the master whenever a new posting appears.
Why this matters now
A job search produces many candidate-facing surfaces, but they should all draw from the same evidence. Without a shared source, tailoring often becomes uncontrolled rewriting: each application changes wording, emphasis, and sometimes facts. AI can help maintain consistency by mapping requirements to verified evidence and by showing exactly where each draft statement came from. The model remains an analyst and transformation engine, while the reader approves the strategy, rewrites the language, and owns every statement that reaches a hiring human.
Act as a career-asset systems analyst, evidence auditor, and tailoring coach. Build a reusable source system from my verified history. Do not act as my ghostwriter, and do not produce final candidate-facing language that I can submit without reviewing and rewriting it.
I may provide:
- My target-role spec sheet
- My current résumé
- My LinkedIn profile text
- My achievement inventory
- Three to five representative job postings
- Portfolio or project notes
If an essential input is missing, identify it. Continue with what is available, but label limitations clearly.
Nonnegotiable rules:
- Use only facts supported by my materials or confirmed by me.
- Never invent or estimate metrics, dates, titles, responsibilities, credentials, tools, or outcomes.
- Separate direct evidence, reasonable interpretation, and unsupported gaps.
- Do not assert how a specific applicant-screening product ranks or rejects candidates.
- Do not promise that a résumé format, keyword pattern, or score will pass screening.
- Preserve a traceable connection between every proposed claim and its source.
- Ask before resolving contradictions between documents.
Work in seven stages.
Stage 1 — Source-of-truth ledger
Create a fact ledger. Assign each usable fact a unique ID. Record the source, role, dates, action, context, result, verification status, confidentiality concerns, and any conflicting versions. Do not rewrite résumé content yet.
Stage 2 — Target-market language map
Analyze the target-role spec and representative postings. Group recurring language into capabilities, responsibilities, tools, outcomes, credentials, and context. Separate broadly recurring language from wording found in only one posting. Do not treat frequency as proof of importance, and do not infer hidden screening rules.
Stage 3 — Evidence coverage matrix
Map each target capability to the strongest fact IDs. Label the coverage strong, partial, adjacent, missing, or unverifiable. Explain the rating. For gaps, propose a verification question, learning action, portfolio proof, or honest omission—never a fabricated claim.
Stage 4 — Positioning architecture
Propose three evidence-based positioning directions. For each, provide the central value proposition, strongest supporting fact IDs, roles it fits, risks or overclaims to avoid, and language that would sound generic. Ask me to choose or revise one direction before continuing.
Stage 5 — Master asset build
Using the approved direction, create:
1. A master-résumé architecture containing all relevant verified experience, projects, skills, education, and credentials.
2. Draft résumé content linked to fact IDs.
3. A LinkedIn alignment plan for headline, About section, experience, skills, featured items, and project evidence.
4. A positioning-story kit containing a one-sentence introduction, a short networking version, and a ninety-second interview outline.
5. A list of evidence that belongs in a portfolio or supporting document rather than the résumé.
Candidate-facing drafts must be labeled DRAFT FOR HUMAN REWRITE.
Stage 6 — Tailoring engine
Design a repeatable procedure for a new job posting. It must:
1. Extract the posting’s explicit priorities.
2. Compare them with the evidence coverage matrix.
3. Select the most relevant verified fact IDs.
4. Recommend what to emphasize, compress, reorder, or omit.
5. Produce a tailored résumé draft without changing the source facts.
6. Produce a change log showing every difference from the master and the evidence behind it.
7. Flag any wording that requires verification or could overstate the candidate’s role.
8. End with a human-ownership pass.
Include a reusable mini-prompt I can paste with each future posting.
Stage 7 — Quality and integrity review
Audit the system for contradictions, unsupported claims, generic AI phrasing, unexplained terminology, confidentiality risks, excessive length, and statements I may struggle to defend aloud. Create a final approval checklist requiring me to verify the facts, rewrite the candidate-facing language, and confirm that every statement sounds like me.
Use clear sections and concise structured lists. Pause for my decision when a strategic choice affects the rest of the system. Do not silently choose a positioning story for me.
Here are my materials:
[PASTE OR ATTACH MATERIALS]
How the AI reads this prompt
Practical examples from different industries
Senior project manager pursuing product-operations roles:
The candidate supplies a target-role spec, a current résumé, LinkedIn text, an achievement inventory, and four representative postings. The system discovers that the résumé emphasizes project delivery while the market repeatedly asks for operating cadence, cross-functional decision support, launch readiness, and process design. It maps those capabilities to verified project facts, proposes three possible positioning directions, and waits for the reader’s choice. The master then preserves the full project history, while each tailored variant selects evidence appropriate to the posting and records every change from the source.
Manufacturing supervisor moving into continuous improvement:
The reader’s materials contain overlapping numbers, inconsistent job titles, and confidential customer names across an old résumé, annual reviews, and project notes. The source ledger flags the conflicts and asks the reader to resolve them instead of silently selecting a version. The market-language map identifies recurring concepts such as root-cause analysis, standard work, throughput, safety, waste reduction, and cross-shift adoption. The expected system links each claim to a verified source and gives the reader an honest view of which target capabilities are strong, adjacent, or still unsupported.
Academic researcher entering an industry role:
A researcher has publications, teaching, grant work, data analysis, and cross-institution collaboration, but LinkedIn presents them almost entirely through academic titles. The advanced prompt maps representative industry postings, separates genuine transferable capabilities from field-specific gaps, and proposes positioning options such as research operations, applied analysis, or program evaluation. It then builds a master résumé that retains important scholarly evidence, a LinkedIn plan written for a broader audience, and a tailoring process that changes emphasis without pretending the candidate has commercial experience they do not possess.
Creative use case ideas
- Build a source-of-truth system for a multi-disciplinary creative portfolio spanning design, writing, teaching, and community work. - Maintain verified biographies of different lengths for conferences, professional associations, volunteer boards, and media introductions. - Help a student create a master experience inventory from coursework, clubs, part-time employment, competitions, and personal projects. - Organize a family historian’s archive so short biographies and longer narratives draw from the same documented facts. - Create a promotion packet, annual-review narrative, and internal profile from one evidence ledger rather than separate recollections.
Adaptability tips
The system can be scaled down by reducing the number of stages. A reader with a verified achievement inventory may begin at the evidence coverage matrix. Someone with only a résumé and one posting can create a smaller ledger, map the posting, and design the master architecture before adding LinkedIn.
The schema can also be customized. Technical candidates may add system scale, reliability, security, and architecture fields. Designers may add audience, design decision, artifact, constraint, critique, and portfolio evidence. Leaders may add decision scope, organizational level, budget authority, team structure, change adoption, and stakeholder consequences.
For ongoing maintenance, add new facts to the ledger before adding them to the master résumé. Review the positioning architecture when the target role changes materially, not for every individual posting. Archive tailored variants and their change logs, but keep the ledger and master as the authoritative sources.
Pro tips
- Store a
safe disclosureversion beside any fact involving confidential clients, security events, regulated data, or unreleased work. - Give every tailored document a version name containing the employer, role, and date while retaining a link to the master version used. - Ask a second AI conversation to audit the final draft using only the résumé, posting, and evidence ledger—not the first model’s reasoning. - Periodically search the master for unsupported adjectives, duplicated evidence, stale terminology, unresolved placeholders, and facts whose verification status has changed.
Prerequisites
The best starting package includes a Week 2 target-role spec sheet, current résumé, LinkedIn text, achievement inventory, and three to five representative postings. The system can begin with less, but incomplete inputs should remain labeled. Gather documents that can resolve conflicting dates, titles, metrics, and project descriptions.
Choose a safe place to maintain the ledger and master assets. Avoid placing highly sensitive employer data, protected personal information, security details, private customer records, or confidential financial information into a public AI service. Replace sensitive names with consistent neutral identifiers so evidence remains traceable without revealing it.
Required tools
Use a general-purpose AI assistant with enough context capacity to compare several documents and maintain structured information across a long conversation. A spreadsheet, database, or structured notes tool is recommended for the fact ledger and coverage matrix. A word processor is needed for the master résumé and tailored variants.
File-upload support is useful but not mandatory if materials are pasted in controlled sections. Version history or cloud storage is strongly recommended so the master, tailored variants, and change logs do not become confused.
Frequently asked questions
Is a master résumé supposed to be submitted to employers?
Usually not. The master is the complete internal source from which shorter, relevant versions are created. It can contain more projects, achievements, skills, and explanatory detail than any employer needs to see. Its purpose is to prevent rediscovery and factual drift, not to satisfy a page target or serve every audience at once.
How many job postings should I use to build the language map?
Three to five representative postings are enough to reveal useful patterns without turning the exercise into an uncontrolled research project. Choose roles that genuinely fit the same target rather than mixing several unrelated career directions. The postings are evidence of market language, not proof of hidden screening rules. Update the map when the target changes or when newer postings show that the language has materially shifted.
Will this system make every application take longer?
The initial build requires more work because it converts scattered career history into verified infrastructure. Later tailoring should become faster because the evidence, positioning choices, and reusable components already exist. The change log also reduces review time by showing exactly what changed. The purpose is not maximum application volume; it is controlled reuse without sacrificing accuracy or ownership.
What happens when two documents contain different numbers or dates?
The system should preserve both versions, identify their sources, and ask you to resolve the conflict. Do not let the AI choose the larger number, the cleaner date, or the newest-looking title simply because it makes a stronger draft. Check employment records, project documents, reviews, calendars, or other reliable evidence. If the discrepancy cannot be resolved, use the most defensible wording or omit the disputed detail.
How do I keep the final materials from sounding AI-written?
Do not treat the generated prose as finished. Rewrite the drafts in your normal vocabulary, vary sentence patterns, remove inflated abstractions, and replace generic claims with concrete facts. Read the material aloud and answer likely interview questions from it. When a sentence is true but sounds unlike you, keep the evidence and change the language.
Recommended follow-up prompts
- New-Posting Tailor: “Using my master résumé, fact ledger, evidence matrix, and the new posting below, select the relevant fact IDs and create a change-controlled tailored draft.” - Cross-Surface Consistency Audit: “Compare my résumé, LinkedIn profile, portfolio introduction, and interview positioning outline for contradictions, unexplained changes, unsupported claims, and mismatched emphasis.” - Quarterly Asset Maintenance: “Review new projects and achievements since the last update, interview me for missing evidence, and show exactly what should be added to the ledger and master assets.”
Tags and categories
Tags:
master résumé, résumé system, LinkedIn positioning, tailoring engine, evidence ledger, career narrative, job-search workflow, prompt chaining
Categories:
Career Development, Advanced AI Workflows
Citations
- Assignment basis for building a master résumé, LinkedIn alignment, and reusable tailoring engine: - Series dependency chain connecting this week’s assets to later application, interview, and negotiation work: - Editorial requirement that the three tiers use genuinely different approaches rather than longer versions of one prompt: - External citations: NOT APPLICABLE.
Which of the three should you use?
The Beginner prompt solves the most immediate problem: a résumé that does not clearly answer one real job description. It is the right choice when the reader has a credible work history, sees an opening worth considering, and wants a controlled revision without building an entire career system. Its strength is focus. It produces a role map, an evidence comparison, a small set of supported revisions, and an editing checklist that can be completed in one sitting.
The Intermediate prompt moves upstream. Instead of assuming the résumé contains all the useful evidence, it interviews the reader to recover achievements, scale, decisions, constraints, and results that were never documented well. It is the best choice when the résumé feels thin, generic, duty-heavy, or disconnected from what the person actually accomplished. The resulting achievement inventory becomes raw material for more than one application.
The Advanced prompt combines the week’s assets into infrastructure. It is designed for a reader pursuing several related roles, maintaining multiple public surfaces, or repeatedly tailoring materials. The initial setup is heavier, but it reduces factual drift and repeated work by giving every future application the same verified foundation. Readers do not need to begin at the advanced level: the Beginner résumé pass can expose missing evidence, the Intermediate interview can fill it, and those outputs can later become the ledger and master system.
TAGS:
