The Role Compass: Interviewing Yourself Before Anyone Else Does
WEEK 101 :: 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: "Defining the Target — What Job Are You Actually Hunting?"
This is Week 2 of an eight-week series on running a job search with AI. Week 1 ended with a written decision to go (or a decision to stay, in which case this series waits patiently). Week 2 exists because of the most common mistake in job searching: "open to anything" is the job-search equivalent of walking onto the car lot with no budget. It produces scattershot applications, generic materials, and a search that runs on other people's job postings instead of the reader's own criteria.
This is also the week to let the series frame surface as good news rather than a warning: the spec sheet is exactly the private, behind-the-scenes analyst work this series says AI is for. No hiring human will ever read it, so the reader gets AI at full analytical power with zero authenticity risk — and the post can say so, briefly and in its own voice.
The work this week is definition: same role somewhere better, a pivot to a different role, or a level-up; full-time employee or contract; remote, hybrid, or onsite; big company or startup. These are trade-offs, not preferences — more of one usually costs some of another — and the reader needs them scored against their own priorities before the search starts, because every later week in this series filters through this answer.
The deliverable the reader should walk away holding: a target-role spec sheet — the role (or two) they are hunting, the must-haves, and the deal-breakers — the document every later week references, from the résumé build to the final offer matrix.
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:
- Define the ideal role from the inside out. A worksheet-style interview that pulls out what the reader actually wants more of and less of — drawing on the Week 1 audit where it exists — before any job title gets written down.
- Score the trade-offs honestly. A structured analysis of compensation vs. growth vs. stability vs. flexibility (and the sub-trades inside each: startup equity vs. big-company benefits, remote freedom vs. in-room visibility), scored against the reader's own stated priorities rather than a generic ranking.
- Build the target-role matrix. The full spec sheet: one or two target roles, the non-negotiable must-haves, the explicit deal-breakers, and the level and range the reader is aiming for — written down so the reader can reject a tempting-but-wrong posting in thirty seconds.
At the advanced tier, the strongest version of this week is a matrix the reader can actually filter with — target roles as rows, must-haves and deal-breakers as testable criteria, and a scoring rule that turns "hmm, maybe" postings into a yes or a no. Vague criteria produce vague searches; a spec sheet with teeth is the deliverable worth reaching for.
A constraint carried from Week 1. AI models cannot see live market data. No prompt may ask the AI to assert which roles are growing, what a pivot "typically" pays, or how a market is trending, as fact. Where the reader needs market reality — whether their target level is realistic, what adjacent roles exist — the prompt should have the AI generate the questions and name the kinds of sources to check (pay-transparency postings, official labor data, people actually in the role), with the reader doing the confirming.
Design the prompts so the AI does what it is genuinely good at: structured elicitation, making trade-offs explicit and scoreable, and turning preferences into testable criteria. The reader supplies their priorities and their Week 1 artifacts; the AI supplies structure and honest trade-off pressure. Posts whose prompts have the AI assert market facts or hand the reader a target without their input should expect to be marked down on Practical Utility and Content Accuracy.
Series dependency chain, for the Metadata block: Week 2 consumes Week 1's written decision and compensation baseline (the "go" decision sets the energy; the baseline sets the floor for the range). Week 2 produces the target-role spec sheet with must-haves and deal-breakers — consumed by Week 3 (assets built against the spec), Week 4 (companies screened against it), Week 7 (deal-breakers anchor the negotiation), and Week 8 (the final offer is scored against this sheet).
Because readers may arrive at this post without having read Week 1, the prompts should work for someone who simply knows they are looking, while making clear the spec sheet is sharper when it is built on a real Week 1 decision and baseline.
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. An engineer deciding between a same-role move and an engineering-management level-up, a marketer weighing startup equity against enterprise stability, and a contractor deciding whether to go back to full-time 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: 2` 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 assert which roles or markets are growing, or what a role typically pays, as fact. Market questions get pointed at named sources the reader checks; the spec sheet is built from the reader's own priorities.
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.
“Open to anything” sounds flexible, but it leaves your job search with no filter, no priorities, and no reliable way to recognize a good opportunity. This week’s three prompts help you define the work you want from the inside out, score the trade-offs that come with it, and build a target-role system strong enough to reject an attractive but wrong job in thirty seconds. By the end, you will have something more useful than a list of job titles: a written specification for the next role you are willing to pursue.
The Role Compass Interview
Turn vague job hopes into one clear, usable target.
A job title is often the last thing you should choose, not the first. Two positions with the same title can differ wildly in workload, autonomy, management quality, travel, schedule, and actual day-to-day responsibilities. Starting with titles encourages you to borrow the employer’s definition of a good job before you have written your own. This prompt reverses that sequence. It interviews you about the work you want more of, the conditions you want less of, and the compromises you are willing to make before it helps you name a target role.
Why this matters now
Job boards are designed to make browsing easy, which can quietly turn searching into reacting. A well-written posting appears, you imagine yourself in it, and your standards begin bending around the opportunity. The Role Compass Interview gives you a private reference point before that happens. Because no employer will see this document, you can use AI freely as an analyst: let it organize your thinking, challenge contradictions, and turn scattered preferences into criteria you can actually use.
Act as a practical job-search analyst. Help me define the kind of role I should target before I begin searching or rewriting application materials.
Interview me one question at a time. Do not recommend job titles during the first part of the interview. Begin by asking what I want more of in my next role, what I want less of, which parts of my current or most recent work give me energy, and which parts consistently drain it.
Then ask about the conditions surrounding the work: compensation floor, employment type, work location, schedule, travel, company size, management style, level of responsibility, opportunities to learn, stability, autonomy, benefits, and any personal constraints that affect the decision.
When I give a vague answer such as ‘better culture,’ ‘more flexibility,’ or ‘good growth,’ ask me for a concrete example. Help me turn each preference into something observable or testable.
After the interview, propose no more than two target-role hypotheses. Base them only on what I told you. Do not claim that a role is growing, typically pays a certain amount, or is in demand. Clearly label anything that requires outside verification.
Create a one-page target-role brief containing:
1. My primary target-role hypothesis.
2. An optional secondary target-role hypothesis.
3. The work I want more of.
4. The work I want less of.
5. Five to seven must-haves.
6. Five to seven deal-breakers.
7. My compensation floor and any unresolved range questions.
8. My preferred employment type and work arrangement.
9. The evidence I should look for in a job posting.
10. Questions I must answer through outside research or conversations.
11. A thirty-second test I can use to reject a poor-fit posting.
End by asking me to correct anything that does not sound like me. Remind me that this is a private analytical draft. I should revise and own the final criteria before using them to guide my search.
How the AI reads this prompt
Practical examples from different industries
Illustrative example — an engineer considering management:
A software engineer enters the interview believing the next logical step is engineering management. During the questioning, he realizes that mentoring junior developers energizes him, but performance reviews, staffing disputes, and calendar-heavy work do not. The prompt helps him define two hypotheses: senior individual contributor at a company with technical mentorship responsibilities, or staff engineer with cross-team influence. His target-role brief prevents him from applying reflexively to management jobs that contain the status he wants but the daily work he dislikes.
Illustrative example — a marketer choosing between company types:
A marketing manager says she wants “more growth” and “less chaos.” The AI asks what those phrases mean in observable terms. She defines growth as owning a larger budget, learning from an experienced leader, and having a path to director-level responsibility; she defines chaos as priorities changing without documented decisions and launches occurring without sufficient preparation. Her target brief does not choose startup or enterprise for her. It gives her criteria she can use to investigate either environment.
Illustrative example — a contractor considering full-time work:
An independent project manager is tired of finding the next engagement but values control over his schedule. The interview surfaces a genuine trade-off: he wants predictable income and benefits without losing all autonomy. His brief identifies a full-time role with flexible scheduling as the primary hypothesis and longer-term embedded contracts as the secondary hypothesis. It also lists mandatory questions about meeting load, core hours, outside work, and decision authority before he treats any posting as a serious opportunity.
Creative use case ideas
- Use the interview before requesting an internal transfer so you can distinguish “I need a new company” from “I need different work.” - Adapt it for a return-to-work decision after caregiving, illness, military service, or an extended break. - Use it to define the right volunteer leadership role in a community or nonprofit organization. - Run the interview before choosing a graduate program, certification, apprenticeship, or career-change boot camp. - Use it with a creative practice to decide whether you want employment, commissions, teaching, licensing, or independent studio work.
Adaptability tips
Replace the job-search categories with constraints specific to your situation. A shift worker may need questions about schedule rotation, overtime, and advance notice; a consultant may care more about utilization targets, travel, and business-development expectations; a parent may need to define school-day availability precisely. You can also shorten the deliverable to one target role if you already know the field, or widen the interview temporarily if you are making a major career change. Keep the final output narrow even when the exploration is broad.
Pro tips
- Paste your Week 1 decision and compensation baseline before starting so the AI can test the new target against what you already established. - Ask the AI to quote the exact statements from your answers that support each must-have or deal-breaker. - Review the brief after a week of browsing postings. Revise criteria that are impossible to observe or too vague to filter with. - Ask a trusted person to challenge one criterion you may be treating as non-negotiable without enough evidence.
Prerequisites
You need only a willingness to answer honestly. The prompt works better if you have your Week 1 decision, compensation baseline, recent performance feedback, a list of tasks you enjoy and dislike, or notes from past job searches. None of those are required. Do not begin with a polished career narrative; rough examples are more useful than carefully managed answers.
Required tools
Any general-purpose conversational AI tool that can conduct a multi-turn interview. A free tier is sufficient if it supports a conversation long enough to complete the questioning and final brief. A notes application or document editor is useful for saving and revising the final target-role specification.
Frequently asked questions
What if I do not know what I want?
That is an appropriate starting point for this prompt. Begin with concrete experiences rather than career labels: work that felt satisfying, situations you dreaded, managers you worked well with, and conditions that made good work harder. The AI can organize those examples into themes, but it should not invent a target that your answers do not support.
Can I use two target roles without making the search too broad?
Yes, provided the roles share enough criteria that one search system can evaluate them. A primary and secondary target can be useful when you are deciding between a same-role move and an adjacent role. If the two roles require entirely different stories, skills, industries, and compensation assumptions, create separate specifications rather than combining them.
What if my must-haves eliminate most jobs?
That may indicate either healthy clarity or unrealistic rigidity. Separate true requirements from strong preferences, then ask what consequence each requirement protects you from. Verify market realities through current postings, official labor information, and conversations with people doing the work before weakening a boundary simply because it reduces the number of results.
Should I share this document with recruiters?
Usually, no. It is a private analytical tool, not an application document. You can use it to ask sharper questions and explain what you are targeting, but rewrite those explanations in your own natural language rather than sending the AI-produced brief.
Recommended follow-up prompts
- A prompt that converts the target-role brief into a résumé evidence inventory without drafting final résumé language. - A company-screening prompt that compares employers against the must-haves and deal-breakers. - A job-posting triage prompt that extracts evidence, uncertainties, and disqualifiers from each posting.
Tags and categories
Tags:
job search, target role, career planning, job criteria, must-haves, deal-breakers, AI interview, career change
Categories:
Career Development, Practical AI Prompts
Citations
NOT APPLICABLE
The Trade-Off Scorecard
Score competing career priorities before opportunities start scoring you.
Most job seekers do not lack preferences. They lack a method for deciding which preference wins when two of them collide. Higher compensation may come with less flexibility. A startup may offer broader responsibility but weaker stability. A remote role may improve daily life while reducing the in-room visibility a particular career path rewards. The Trade-Off Scorecard does not pretend those tensions can be eliminated. It asks you to weight them, define what each one means, and examine the cost of choosing more of one at the expense of another.
Why this matters now
Career decisions become harder when every option is described with positive language. “Fast-paced,” “high visibility,” “flexible,” and “entrepreneurial” can conceal very different working conditions. A weighted scorecard forces each phrase to compete against your actual priorities rather than your mood when you encounter the posting. The AI’s role is to structure the comparison, reveal contradictions, and identify missing evidence. It is not allowed to manufacture salary facts, market demand, or certainty where your information is incomplete.
Act as a decision analyst helping me create a weighted scorecard for my next role. Your job is to make my trade-offs explicit, not to choose a career for me or write application materials.
Begin by asking whether I have a Week 1 job-search decision, compensation baseline, or existing target-role notes. If I do, ask me to paste them. If I do not, continue with the information I can provide now.
Interview me about four top-level priorities:
1. Compensation.
2. Growth.
3. Stability.
4. Flexibility.
Help me define what each priority means in my situation. Break broad categories into relevant sub-factors. Examples may include base pay, variable pay, benefits, equity, skill development, promotion path, quality of mentorship, company durability, employment type, schedule control, work location, travel, autonomy, and workload predictability.
Ask me to assign weights totaling 100 points across the priorities and sub-factors. If my weights conflict with statements I made earlier, identify the contradiction and ask me to resolve it.
Ask me for up to three role hypotheses or opportunity types I am considering. These may be job titles, employment arrangements, company types, or career directions.
Score each option from 1 to 5 on every criterion, but use only evidence I provide. When evidence is missing, write ‘UNKNOWN’ instead of estimating. Do not assert current salary ranges, hiring demand, company stability, or market trends. Put those items on a verification list.
For each option, produce:
1. A weighted score.
2. The strongest reason it fits.
3. The most expensive compromise it requires.
4. Any hard requirement it fails.
5. The unknowns that could change the result.
6. The evidence needed to resolve those unknowns.
7. A provisional decision: pursue, investigate, hold, or reject.
Then run three stress tests:
- Compensation increases by 15 importance points.
- Flexibility increases by 15 importance points.
- Stability increases by 15 importance points.
Rebalance the remaining weights proportionally and explain whether the recommendation changes.
Finish with a concise target-role scorecard I can save. Include my criteria, weights, hard requirements, deal-breakers, current role hypotheses, unresolved questions, and the date I should review the scorecard again.
Remind me that the scorecard is a decision aid, not objective truth. I should verify outside facts through current pay-transparency postings, official labor information, employer materials, and conversations with people who know the role. Anything I say to an employer must be rewritten in my own words and remain completely true.
How the AI reads this prompt
Practical examples from different industries
Illustrative example — a marketer comparing startup and enterprise roles:
A senior marketer weighs a startup role offering broad ownership and possible equity against an enterprise role offering stronger benefits, established processes, and a clearer reporting structure. She initially says growth is her highest priority, but her weights reveal that stability, predictable workload, and health benefits collectively matter more. The scorecard does not declare one company type superior. It shows that the startup remains attractive only if she can verify decision authority, runway, and realistic workload expectations.
Illustrative example — an engineer choosing between leadership paths:
An engineer compares staff engineer, engineering manager, and technical program manager roles. He assigns high weight to technical depth and autonomy, moderate weight to compensation, and lower weight to formal promotion speed. The stress test shows that engineering management becomes the top option only when promotion path receives much more importance than he originally gave it. That result helps him see that management appeals partly because it is visibly recognized, not because its daily responsibilities best match his priorities.
Illustrative example — a healthcare contractor considering employment:
A specialized healthcare contractor compares remaining independent, joining a staffing firm, and accepting a direct full-time role. The full-time option scores well on stability and benefits but contains unknowns around schedule control and mandatory overtime. Instead of estimating, the AI marks those fields unknown and creates interview questions. The result remains provisional until she gathers evidence, preventing a high weighted score from disguising the two facts most likely to change her decision.
Creative use case ideas
- Compare an internal promotion with an external move using the same criteria. - Evaluate whether to return to full-time employment after freelancing or consulting. - Score graduate programs, apprenticeships, fellowships, or professional certifications against cost, flexibility, and career value. - Help a nonprofit volunteer decide between board service, committee leadership, and project-based contribution. - Compare a stable role that preserves time for creative work with a more exciting role that consumes that time.
Adaptability tips
Add or remove sub-factors while keeping the four top-level categories understandable. A sales professional might add territory quality, quota design, and commission reliability under compensation and stability. A researcher might add publication freedom, grant dependence, laboratory resources, and principal-investigator support. You can also change the stress tests to reflect the decision you fear most, such as losing remote work, accepting a lower title, or choosing a company with uncertain funding. Keep the total weight at 100 so every change has a visible cost.
Pro tips
- Set hard gates before scoring. An option that violates a true deal-breaker should not win merely because it earns points elsewhere. - Ask the AI to distinguish evidence, interpretation, assumption, and unknown for every score. - Run the scorecard twice: once with your stated weights and once using weights inferred from your recent real-world decisions. - Save the version date. A scorecard built before a major family, health, financial, or career change should not govern decisions indefinitely.
Prerequisites
Prepare any Week 1 decision, compensation floor, existing target-role brief, and up to three options you are considering. You do not need complete information about those options; unknowns are expected. You should, however, be prepared to define what compensation, growth, stability, and flexibility mean in concrete terms for your own situation.
Required tools
A general-purpose conversational AI tool capable of handling multi-step instructions and basic arithmetic. A spreadsheet can be useful for maintaining the scorecard over time, but it is optional. The prompt can produce a readable plain-text scorecard in any standard AI interface.
Frequently asked questions
Are numerical scores really useful for a personal career decision?
They are useful when treated as a way to expose assumptions, not as a machine-generated verdict. The score forces you to define priorities and notice where evidence is missing. Its value comes from the discussion behind the number, especially the compromises and unknowns.
What if two options receive almost the same score?
Treat that as evidence that the current information cannot support a clear choice. Look at hard requirements, the most expensive compromise, and which unknowns could create separation. A near tie often tells you exactly what to investigate next.
Can the AI choose the weights for me?
It can suggest a draft based on your statements, but you should approve every weight. A model may overemphasize factors that are commonly discussed while missing a constraint that is personally decisive. Ask it to explain the evidence behind suggested weights, then change them until they reflect your real priorities.
How often should I update the scorecard?
Review it when your circumstances change, when repeated job postings reveal that a criterion is poorly defined, or when you learn something important about the roles. It is also useful to review before serious interviews and again before evaluating an offer. A version date prevents old priorities from quietly controlling a new decision.
Recommended follow-up prompts
- A research-question generator that turns every unknown score into a verification task and names appropriate source types. - A job-posting evidence extractor that maps posting language to the scorecard without inventing missing facts. - An offer-comparison prompt that reuses the same weights while separating confirmed terms from assumptions.
Tags and categories
Tags:
job search, career trade-offs, weighted scoring, decision analysis, compensation, growth, stability, flexibility, role comparison
Categories:
Career Development, Decision-Making Prompts
Citations
NOT APPLICABLE
The 30-Second Role Filter
Build a reusable system that filters roles before enthusiasm interferes.
A sophisticated job search needs more than preferences and a weighted average. Some criteria should earn points, some should trigger investigation, and some should end consideration immediately. Combining all three types into one score can produce absurd results: a job may appear attractive overall while violating the one condition that makes it impossible. The 30-Second Role Filter creates a reusable decision system with hard gates, weighted criteria, evidence rules, and a fast posting screen. It is designed for readers who want the target-role specification to control the search, not merely describe it.
Why this matters now
Job postings are persuasive documents. They foreground possibility, compress ambiguity, and often leave crucial working conditions unstated. The longer you spend imagining yourself in a role, the harder it becomes to reject it cleanly. A prebuilt filter moves the decision criteria ahead of the emotional reaction. AI is particularly useful here because the work is private and structural: it can normalize criteria, test edge cases, expose loopholes, and help you build a system that behaves consistently across dozens of postings.
Act as a job-search systems designer and decision auditor. Help me build a reusable target-role decision system that can screen job postings, guide employer research, and later support offer evaluation.
Do not write résumé content, cover letters, outreach messages, interview answers, or negotiation language. Anything a hiring human will see or hear must remain true and must be written in my own words.
Begin by collecting the following inputs:
- My Week 1 decision and compensation baseline, if available.
- One or two target-role hypotheses.
- The responsibilities I want more of.
- The responsibilities I want less of.
- My preferred level, employment type, work arrangement, company environment, and scope.
- My must-haves, strong preferences, tolerable compromises, and deal-breakers.
- Any personal constraints that should affect the system.
Challenge vague criteria. Convert each one into an observable test, a question I can ask, or evidence I can gather. If a criterion cannot be tested, help me rewrite it.
Create three criterion types:
1. HARD GATES: requirements that immediately disqualify an opportunity when clearly failed.
2. WEIGHTED CRITERIA: factors scored from 0 to 5 and multiplied by a weight.
3. WARNING FLAGS: conditions that do not automatically disqualify the role but require investigation.
Require all weighted criteria to total 100 points. Do not allow the score to override a failed hard gate.
For each target-role hypothesis, create a structured role record containing:
- Role label.
- Core purpose.
- Desired level and scope.
- Responsibilities expected.
- Responsibilities to avoid.
- Required conditions.
- Preferred conditions.
- Acceptable compromises.
- Deal-breakers.
- Evidence sources.
- Unresolved assumptions.
Then create a posting-screen process with four stages:
STAGE 1 — Thirty-second rejection screen: Check only for obvious hard-gate failures and direct conflicts with the target-role record.
STAGE 2 — Evidence extraction: Separate confirmed posting evidence, ambiguous wording, missing information, and possible warning flags.
STAGE 3 — Weighted fit: Score only criteria supported by evidence. Mark unsupported criteria UNKNOWN. Calculate a confirmed-evidence score and show how much of the total weight remains unresolved.
STAGE 4 — Human decision: Return one result: reject, hold for research, pursue lightly, or pursue actively. Explain the result using the failed gates, confirmed score, unresolved weight, and highest-risk assumption.
Add these system rules:
- A failed hard gate always produces reject unless I explicitly revise the gate.
- Unknown information never receives an assumed positive score.
- Attractive compensation does not erase a failed deal-breaker.
- A famous company, impressive title, or persuasive posting does not receive bonus points unless it satisfies a written criterion.
- The AI may identify questions and source types, but it may not assert current pay, demand, growth, or market conditions as fact.
- All outside facts must be verified through current sources.
- Every criterion must have an owner: confirmed by me, confirmed by the posting, confirmed through research, or unresolved.
Next, stress-test the system with five hypothetical edge cases:
1. High compensation but one failed flexibility gate.
2. Perfect responsibilities but unclear level and authority.
3. Strong overall fit with several important unknowns.
4. Prestigious employer with weak evidence of actual fit.
5. Secondary target role that scores higher than the primary role.
For each edge case, show how the rules prevent an impulsive or inconsistent decision. If the system produces a result that contradicts my stated priorities, revise the rules with me.
Finally, produce:
1. My target-role system.
2. A compact thirty-second rejection checklist.
3. A deeper research checklist.
4. A reusable plain-text evaluation form for future postings.
5. A list of unresolved market questions and the kinds of current sources I should check.
6. A version number and review date.
7. A short explanation of what would justify changing a hard gate, weight, or target-role hypothesis.
End with a quality audit. Identify criteria that remain vague, duplicated, untestable, easy to manipulate, or overly dependent on information a posting is unlikely to provide. Ask me to approve the final system before I use it.
How the AI reads this prompt
Practical examples from different industries
Illustrative example — a security professional screening leadership roles:
A senior cybersecurity practitioner is considering incident-response manager and principal incident responder positions. The system treats on-call expectations, decision authority during major incidents, and the percentage of time spent on people management as testable criteria. A prestigious management opening fails the screen because the posting explicitly requires a level of travel that violates a hard gate. The title and compensation never reach the weighted stage because the system has already identified a disqualifying condition.
Illustrative example — a product leader comparing scope claims:
A product manager wants a director-level role with genuine portfolio ownership. Several postings use phrases such as “strategic leadership,” but provide little evidence about budget authority, team size, roadmap ownership, or executive access. The filter marks level and authority as unresolved rather than awarding points for the title. One role remains on hold for research, while another advances because the posting describes specific decision rights and cross-functional scope that match the written target-role record.
Illustrative example — a designer returning to employment:
An independent designer is considering agency, in-house, and design-systems roles after years of freelance work. The system includes a hard gate against routine speculative work, weighted criteria for craft depth, collaboration, schedule predictability, and compensation, plus warning flags for vague ownership language. An in-house posting scores lower than expected because much of its apparent fit depends on assumptions. A design-systems role becomes the stronger target after confirmed responsibilities align with the designer’s desired mix of creative work and structured problem-solving.
Creative use case ideas
- Build separate filters for an internal promotion, an external move, and a contract path without combining them into one vague target. - Adapt the system to screen board positions, advisory roles, or long-term volunteer commitments. - Evaluate graduate programs or fellowships using hard gates for cost and location, weighted criteria for mentorship and outcomes, and warnings for unclear funding. - Create a creative-project filter for commissions, exhibitions, collaborations, or publishing opportunities. - Use the same gate-and-weight structure when deciding whether a professional opportunity is worth interrupting a stable current role.
Adaptability tips
The system can be simplified or expanded without changing its logic. For a narrow same-role search, use one target-role record and fewer than ten weighted criteria. For a major pivot, maintain separate role records so different paths do not inherit assumptions from each other. You can also create different screening forms for postings, recruiter conversations, interviews, and offers while preserving the same gates and weights. Do not change criteria merely to make a specific opportunity pass; revise the system only when your underlying priorities or verified understanding have changed.
Pro tips
- Add a confidence label to each criterion: high, medium, or low confidence that it belongs in the system. - Require a written change log whenever you alter a gate or weight after seeing an attractive opportunity. - Track false positives and false negatives. Note roles the system advanced that later proved poor, and roles it rejected that later appeared better than expected. - Create a “manipulation test” asking how an employer’s wording could make a weak fit appear to satisfy each criterion.
Prerequisites
Have your Week 1 decision and compensation baseline available when possible. Prepare one or two target-role hypotheses and a rough list of desired responsibilities, unwanted responsibilities, must-haves, preferences, acceptable compromises, and deal-breakers. You do not need to know whether every criterion is realistic yet; market-dependent assumptions should be recorded for verification rather than treated as facts.
Required tools
A general-purpose AI tool with enough context capacity to manage a detailed multi-step prompt and preserve the resulting system during the conversation. A spreadsheet, database, or structured notes tool is helpful for storing multiple role records and posting evaluations, but the prompt is designed to produce a usable plain-text form. No live-data connection is required because current market claims must be verified separately.
Frequently asked questions
Why not use one overall fit score for everything?
A single score hides the difference between a preference and an absolute constraint. A role with excellent pay and responsibilities could still be impossible because of location, schedule, travel, or employment terms. Hard gates protect those boundaries, while weighted criteria compare acceptable options.
What should qualify as a hard gate?
A hard gate should protect a condition whose failure would make the role unacceptable even if everything else looked strong. It should be concrete enough to test and important enough to justify immediate rejection. If you routinely want to waive it for attractive opportunities, it may be a strong preference rather than a true gate.
How do I keep the system from becoming too complicated?
Use the fewest criteria that can reliably distinguish good opportunities from poor ones. Merge duplicates, remove criteria that never affect a decision, and keep the thirty-second screen limited to obvious conflicts. Complexity is justified only when it changes action or improves the quality of evidence.
What happens when a posting omits most of the information I need?
The system should return “hold for research” or “pursue lightly,” depending on the confirmed evidence and the importance of the unknowns. Missing information is not automatically bad, but it should never receive a positive score. Convert the gaps into recruiter questions, interview questions, and research tasks.
Can I use this system to evaluate an offer later?
Yes. The same gates and weights can anchor offer evaluation, but confirmed offer terms should replace posting assumptions. You may also need additional criteria for benefits details, start date, reporting line, severance, equity terms, and negotiation priorities.
Recommended follow-up prompts
- A job-posting parser that fills the evaluation form while preserving exact evidence and marking every inference. - A company-research planner that converts warning flags and unknowns into source-specific research tasks. - An offer-matrix prompt that reuses the target-role system and compares confirmed terms without allowing compensation to erase deal-breakers.
Tags and categories
Tags:
advanced prompting, job search system, target-role matrix, decision rules, hard gates, weighted criteria, job-posting filter, evidence tracking
Categories:
Career Development, Advanced AI Systems
Citations
NOT APPLICABLE
Which of the three should you use?
The Role Compass Interview is the best entry point when the problem is definition. It begins with lived experience rather than job titles and produces a concise target-role brief that a reader can understand and revise quickly. It is deliberately conversational and low-friction. The result is less numerical than the later approaches, but it establishes the language and boundaries those approaches need.
The Trade-Off Scorecard is designed for readers who already have plausible directions but need to decide what matters most. It exposes the cost of each choice by forcing compensation, growth, stability, and flexibility to compete for limited weight. The 30-Second Role Filter goes further by turning the target into an operating system: hard gates reject impossible opportunities, weighted criteria compare viable ones, warning flags direct research, and evidence rules prevent assumptions from receiving credit.
The three variations can also be used as a sequence. Begin with the interview to define the target, use the scorecard to pressure-test the trade-offs, and build the advanced filter when you are ready to evaluate postings repeatedly. Choose the simplest version that will reliably change your decisions. A more elaborate system is useful only when you will maintain and use it.
TAGS:
