WEEK 107 :: 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: "Sticking the Landing — Decision, Resignation, and the First 90 Days."
This is Week 8, the final week of an eight-week series on running a job search with AI. The negotiation is done and a final offer is on the table. Three endings can still go wrong from here: the decision (excitement making the call instead of the Week 2 criteria), the exit (a burned bridge or a counteroffer trap — the current employer suddenly finding money, which the reader should evaluate with open eyes given how often an accepted counteroffer just postpones the departure), and the landing (the sink-or-swim first quarter that decides the story of this job before most people have found the good coffee).
The reader started this series restless in Week 1. This week they finish it: signed, resigned gracefully, and onboarding with a plan — the same full-journey capstone the car series closed on.
The deliverable the reader should walk away holding: a scored final decision, a resignation plan with scripts, and a 30/60/90-day onboarding plan with stakeholder map and early wins identified.
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:
- Score the final decision. A weighted decision matrix that scores the final offer (or offers) against the Week 2 spec sheet — must-haves, deal-breakers, and priorities the reader set before any offer existed — so the call is made by criteria written by a calmer version of the same person, with a written record of why.
- Exit gracefully and survive the counteroffer. Resignation scripts for the conversation and the letter, a plan for the awkward two weeks, and a counteroffer framework that has the reader decide their response before the counter comes — including an honest look at why the money appeared only when they stood up to leave.
- Plan the first 90 days. A 30/60/90 onboarding plan built around stakeholder mapping (who decides, who influences, who knows where the bodies are buried), early wins matched to what the reader learned about the team in Weeks 4 and 6, and a cadence for turning a new job into an established position.
At the advanced tier, the strongest version of this week is the complete landing package — decision record, exit plan, and onboarding plan as one coherent handoff from "candidate" to "new hire," each part feeding the next. And because this is the series capstone, the strongest posts can close the loop the reader has lived: eight weeks of artifacts, each built on the last, is a working demonstration that structured, reusable prompting is how a long project holds together — said quietly, as an observation, not a pitch.
A constraint for the last week. Resignations touch contracts and law: notice obligations, non-competes, equity forfeiture, benefits timing — jurisdiction-specific, contract-specific, and not the AI's call. No prompt may ask the AI to interpret the reader's employment contract, state notice or non-compete rules as settled fact, or adjudicate what the reader is legally owed on exit. The scripts handle the human conversation; the contract questions get pointed at the reader's actual documents, HR, and where it matters, a lawyer. Counteroffer statistics follow the series rule: no invented figures — the pattern can be described honestly without a percentage stapled to it.
Design the prompts so the AI does what it is genuinely good at: scoring options against pre-set criteria, drafting graceful language for hard conversations, and structuring ninety days of ambiguity into a plan. The reader supplies the offer, the criteria, and what they learned about the company; the AI supplies the matrix, the scripts, and the calendar.
Series dependency chain, for the Metadata block: Week 8 consumes the whole series — Week 1's decision criteria and baseline, Week 2's spec sheet (the decision matrix scores against it), Week 4's dossier and Week 6's diagnostic reads (the landing plan's intelligence), and Week 7's negotiated outcome (the numbers being decided on). Week 8 produces the signed decision, the exit, and the onboarding plan — and, in the pattern this series inherited from the last one, its real successor is the next reader's Week 1: the restlessness this plan is designed to prevent.
Because readers may arrive at this post with an offer in hand and none of the earlier weeks read, the prompts should work from the offer and the reader's own priorities, while making clear the decision matrix is only as good as the criteria behind it — and criteria written before the offer existed are the trustworthy kind.
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 reader choosing between the offer and a surprise counteroffer, one resigning from a team they love for a role they need, and a new hire mapping stakeholders in their first month 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 — the counteroffer-departure statistic that circulates in this territory is exactly the kind of number to write around, not assert.)
## 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: 8` 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 interpret an employment contract, state notice or non-compete rules as fact, or assert a counteroffer statistic. Contract questions go to the reader's documents, HR, or a lawyer; the decision matrix runs on the reader's own Week 2 criteria. Also confirm resignation and counteroffer-response scripts end in the reader's own words — the series contract's final-pass rule applies to exits too: a resignation letter is read by the humans who will be the reader's references for years.
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 job search is not finished when the offer arrives; it is finished when you make a defensible decision, leave without unnecessary damage, and enter the new role with a plan. This capstone gives you three prompts at three depths: a calm final-offer scorecard, a resignation and counteroffer rehearsal, and a complete landing package that carries your decision through the first 90 days. The point is not to let AI choose your future or speak for you. It is to use AI backstage as an analyst, coach, and sparring partner so the judgment and the words that reach other people remain yours.
The Calm-Headed Offer Check
Score the offer before excitement rewrites your priorities.
The offer call creates a peculiar kind of amnesia. Concerns that mattered for months suddenly feel negotiable, the salary number takes up the whole screen, and relief starts impersonating certainty. The safest counterweight is not another round of intuition. It is a short decision record built from priorities you chose before the offer existed—or, if you are arriving late, priorities you write down before analyzing the package. This beginner prompt turns one offer into a structured yes, no, or not-yet decision without pretending that arithmetic can make the choice for you.
Why this matters now
A weighted scorecard is useful because it forces unlike considerations—pay, flexibility, manager quality, growth, commute, stability, mission, and risk—into one visible decision process. NASA’s systems-engineering guidance uses the same underlying logic for consequential choices: define criteria, rank their importance, compare alternatives, record assumptions, and document the rationale rather than relying on an unexplained conclusion. Your career decision is more personal than an engineering trade study, but the discipline transfers well.
Act as my private decision analyst, not as the person who decides for me.
I have a final job offer. Help me test it against priorities chosen before I get swept up in the moment.
Here is the offer information I know: [PASTE SALARY, BONUS, EQUITY, BENEFITS, LOCATION, SCHEDULE, TITLE, MANAGER, RESPONSIBILITIES, START DATE, AND ANY OTHER VERIFIED TERMS]
Here are my five most important job priorities, in order: 1. [PRIORITY] 2. [PRIORITY] 3. [PRIORITY] 4. [PRIORITY] 5. [PRIORITY]
My non-negotiable deal-breakers are: [LIST THEM, OR WRITE NONE]
First, separate verified facts from assumptions and unknowns. Do not fill missing information with guesses. Ask no more than five questions that could materially change the decision.
Then create a simple scorecard. Weight my priorities 5, 4, 3, 2, and 1 in the order listed. Score the offer from 1 to 5 on each priority, explain each score in one sentence, and mark any score based on incomplete information as provisional.
After scoring, give me:
- Any deal-breaker that was triggered
- The strongest case for accepting
- The strongest case for declining
- The one unknown most worth resolving
- A provisional verdict: accept, decline, or pause for clarification
- A short private decision note explaining the reasoning in plain language
Do not interpret employment contracts, equity documents, non-compete terms, notice obligations, or benefits rules. Instead, list the exact questions I should verify in my documents or ask HR, a benefits professional, or a qualified lawyer.
Treat your output as analysis for me to review. I will make the decision and rewrite any language I use in my own words.
How the AI reads this prompt
Practical examples from different industries
An illustrative manufacturing supervisor has an offer with a 14 percent raise, a better title, and a longer commute. His five priorities are predictable hours, manager quality, compensation, advancement, and proximity to family. The prompt would separate the verified raise and commute from the still-unknown overtime expectations, score the known terms, and mark the schedule score provisional. The most useful output may not be the total. It may be the discovery that the unknown overtime policy could flip the verdict, giving him one precise question to resolve before signing.
An illustrative nonprofit program director receives an offer from a larger organization with stronger benefits but less mission alignment and a six-month probationary period she has not yet examined. She lists mission, autonomy, financial stability, health coverage, and leadership access as her priorities, with a deal-breaker around frequent overnight travel. The prompt would expose whether travel expectations are verified, show where the larger organization wins, and force a written case for declining despite the prestige. That record matters because it protects her from later rewriting the story as “I just had a feeling.”
An illustrative parent returning to the workforce is comparing a single offer against remaining unemployed for another month, not against a second company. His priorities are schedule reliability, health coverage start date, commuting cost, skill growth, and base pay. The prompt can still work because the real alternative is “accept now versus continue searching.” It will not manufacture a perfect answer, but it will make the cost of waiting and the cost of accepting visible, while clearly labeling benefits timing as something to verify with HR rather than guess.
Creative use case ideas
- Re-score a promotion opportunity against the reasons you originally wanted to leave your current team. - Compare a full-time offer with a contract path using the same personal priorities. - Evaluate whether a relocation package compensates for the parts of life the move disrupts. - Use the method for a graduate-school offer, residency placement, fellowship, or apprenticeship. - Run a “future regret” pass by scoring the offer from the perspective of yourself one year from now.
Adaptability tips
For two or more offers, keep the criteria and weights fixed, then score every offer on the same scale. For a late-arriving reader without a Week 2 spec sheet, write the five priorities before pasting the offer details; otherwise the offer will influence the criteria meant to judge it. Add a minimum acceptable score to any true must-have, so a high total cannot hide failure on a critical condition. When compensation is complex, break it into separate criteria only when each component genuinely affects your choice; otherwise one offer with many small perks can earn extra points merely because it has more line items.
Pro tips
- Run the score twice: once with your original weights and once after reducing the top criterion by one point. If the verdict changes easily, the decision is sensitive and deserves more investigation. - Ask the AI to show the calculation for every weighted score. Never trust a total you cannot reproduce. - Date the decision note and save the inputs. The record becomes useful later when you evaluate whether the job matched what was promised. - Ask a trusted person to challenge the priorities, not the arithmetic. The deepest errors usually enter before the scoring begins.
Prerequisites
Have the written offer or verified offer summary available. List five priorities and any true deal-breakers before analysis begins. Gather only facts you can support from the offer, recruiter, hiring manager, benefits materials, or your own notes. If you completed Week 2, use that spec sheet rather than recreating your criteria now.
Required tools
Any general-purpose AI assistant that can follow a multi-step prompt. A free tier is sufficient for one offer with a short input; a paid tier may help if you paste lengthy benefits summaries, but do not paste confidential documents unless you understand the tool’s data settings and your obligations.
Frequently asked questions
What if the highest score still feels wrong?
A score is a decision aid, not a command. Inspect the low-scoring criteria, the provisional scores, and any deal-breakers; the discomfort may be evidence that an important criterion is missing or badly weighted. Add that criterion explicitly and rerun the analysis rather than ignoring the feeling or obeying it blindly. If the feeling remains, write down what the matrix cannot capture and make the final judgment yourself.
Can I use priorities I wrote after receiving the offer?
Yes, especially if you are arriving at the series late, but acknowledge the risk. Once an offer exists, people naturally reshape criteria around the offer’s most attractive features. Write your priorities before asking the AI to score anything, then ask whether each priority reflects a long-term need or merely a reaction to the current package. Criteria written before the offer existed are generally the cleaner baseline because they were not tailored to justify a desired result.
Should I include salary as one criterion or several?
Start with total compensation as one criterion unless base pay, bonus reliability, equity, retirement contributions, or health costs affect you in meaningfully different ways. Splitting one category into many subcategories can unintentionally give money more weight than you intended. If you do separate them, reduce their individual weights so compensation does not dominate simply because it occupies more rows. The structure should reflect your priorities, not the number of fields in an offer letter.
What if the AI makes up an offer detail?
Stop and correct the record before using the score. Ask it to produce a three-part list labeled verified, assumed, and unknown, and require every score to reference one of those categories. A confident explanation attached to an invented fact is still wrong. This is why the prompt asks for uncertainty labeling before arithmetic.
Recommended follow-up prompts
- Offer Clarification Question Builder: Turn the “most important unknown” into a short list of questions for the recruiter, then rewrite the final questions in your own voice. - Decision Sensitivity Check: Recalculate the verdict under different weights and show which assumptions can change the outcome. - Personal Acceptance Checklist: Convert the final decision into a private list of documents, dates, and confirmations to complete before giving notice.
Tags and categories
Tags:
job offer, decision matrix, career criteria, offer evaluation, deal-breakers, job search, AI analysis
Categories:
Career Decisions, Job Search Prompts
Citations
- NASA, Systems Engineering Handbook, Section 6.8 Decision Analysis: criteria, ranking, normalization, assumptions, alternatives, and documented rationale in formal decisions. - MIT BLOSSOMS, Choosing a College Roommate: How Multi-Criteria Decision Modeling Can Help: an accessible explanation of using weighted measures to compare alternatives. - Ketelsen.ai authoring instructions and Week 8 assignment: three distinct difficulty tiers, complete-post requirements, and the capstone’s scored-decision deliverable.
The Graceful Exit Rehearsal
Rehearse the resignation before pressure chooses your words.
Resigning is a short conversation with a long shadow. The manager may be disappointed, the team may feel abandoned, and a counteroffer may arrive before you have had time to remember why you started looking. The danger is not that you will forget the perfect sentence. It is that emotion, guilt, flattery, or surprise will make you improvise a new decision under pressure. This intermediate prompt helps you prepare the conversation, the written notice, the awkward transition period, and the counteroffer response—while requiring you to personalize every human-facing line before it leaves your screen.
Why this matters now
The exit also contains administrative questions that should not be left to an AI’s memory. Health coverage, retirement accounts, final pay, equity, and notice requirements depend on plan documents, employer policy, state law, and personal circumstances. The U.S. Department of Labor advises departing workers to review continuation and marketplace coverage options, while the IRS outlines several possible paths for workplace retirement balances after employment ends. Those are verification tasks, not reasons to let a chatbot interpret your contract.
Act as my private resignation coach and rehearsal partner. Help me leave professionally without speaking for me.
My situation:
- Role and industry: [DETAILS]
- Manager relationship: [DETAILS]
- Team context: [DETAILS]
- Why I am leaving: [PRIVATE REASONS]
- New role start date: [DATE]
- Preferred last day: [DATE]
- What I am willing to share: [DETAILS]
- What I want to keep private: [DETAILS]
- Transition work already in progress: [PROJECTS, CLIENTS, OR RESPONSIBILITIES]
My counteroffer pre-commitment:
- The original reasons I began searching were: [LIST]
- A counteroffer would be worth considering only if: [CONDITIONS, OR WRITE NEVER]
- I will not decide during the resignation meeting. I will request time to think.
Build five outputs.
1. RESIGNATION CONVERSATION REHEARSAL Create a concise conversation outline with an opening, the decision, appreciation, proposed final day, transition commitment, and a boundary for questions I do not want to answer. Give me three tonal versions: direct, warm, and very brief. These are rehearsal drafts only. Flag every phrase that sounds generic, inflated, or unlike a real person.
2. WRITTEN NOTICE DRAFT Create a short resignation-letter draft that states the decision, proposed final day, appreciation, and willingness to support a reasonable transition. Do not include criticism, detailed reasons, legal claims, or promises I may not be able to keep. End with a personalization checklist requiring me to rewrite it in my own words before sending.
3. COUNTEROFFER PLAN Compare any hypothetical counteroffer against my original reasons for leaving. Separate problems that money can fix from problems it cannot fix. Create a decision tree for these cases: no counteroffer, immediate verbal counteroffer, written counteroffer, emotional pressure, and a request for an answer on the spot. Draft short rehearsal responses that buy time without reopening a decision I have already made.
4. TWO-WEEK TRANSITION PLAN Create a practical plan for documentation, handoffs, access ownership, recurring meetings, open risks, stakeholder notifications, and boundaries against taking on new long-term work. Prioritize what protects the team after I leave, not what makes me look heroic.
5. EXIT VERIFICATION CHECKLIST List questions I should verify in my actual offer, employment documents, benefits materials, and employer policies. Include health coverage timing, final pay, unused leave, retirement accounts, equity or bonus dates, return of property, confidentiality, and any notice or restrictive-covenant questions. Do not interpret the documents or state legal rules as settled fact. Route contract-specific questions to HR, the plan administrator, a tax professional, or a qualified employment lawyer as appropriate.
After producing the five outputs, role-play my manager in two short scenarios: disappointed but professional, and surprised with a counteroffer. Ask me to answer aloud in my own words. Then critique my response for clarity, respect, over-explaining, accidental negotiation, and promises I should not make.
Nothing you draft is ready to send as written. I must make it true, specific, and recognizably mine before another person reads or hears it.
How the AI reads this prompt
Practical examples from different industries
An illustrative cybersecurity analyst is leaving a close-knit incident-response team for a role with better hours and broader authority. He respects his manager and worries that explaining the burnout will sound accusatory. The prompt would create a warm but bounded conversation outline, a transition plan for active investigations and access ownership, and a counteroffer response that returns to the schedule problem rather than debating loyalty. During role-play, it might flag his instinct to promise unlimited after-hours help after departure—a generous offer that could create security, legal, and personal complications.
An illustrative public-school administrator is resigning near the end of a planning cycle. She loves the staff but is moving to a district with a shorter commute and clearer advancement path. Her exit requires careful timing, records transfer, and stakeholder communication, while employment terms are governed by documents and local rules the AI should not interpret. The prompt would help her rehearse a respectful conversation, identify questions for HR or her association representative, and build a handoff plan that distinguishes urgent continuity work from projects the successor should own.
An illustrative restaurant general manager receives an immediate verbal counteroffer after giving notice. The owner offers more money and says the team will struggle without him, but his original reasons for leaving include unpredictable scheduling, deferred maintenance, and repeated staffing promises that never became durable changes. The prompt would separate the pay issue from the operating-system issues, remind him of his pre-commitment not to answer on the spot, and rehearse a brief response that expresses appreciation without turning the resignation meeting into an improvised negotiation.
Creative use case ideas
- Rehearse an internal transfer conversation where you are leaving one manager but staying in the company. - Prepare a graceful exit from a volunteer board, community organization, or long-running creative collaboration. - Practice declining a counteroffer when the relationship is warm and the pressure is emotional rather than financial. - Build a handoff plan for a freelancer ending a major client engagement without abandoning open work. - Use the role-play format to prepare for an exit interview while deciding what feedback is useful, specific, and safe to share.
Adaptability tips
For a difficult manager, shorten the conversation outline and increase boundary language; do not use extra explanation as a strategy for winning agreement. For a manager you trust, expand the appreciation and transition sections while keeping the decision itself unambiguous. If your notice period is longer or shorter than two weeks, replace the label with the actual window and ask the AI to prioritize by business risk. For remote resignations, rehearse both a video conversation and a brief written request for the meeting. For internal transfers, change the counteroffer section into a retention or role-redesign discussion while keeping the same rule: decide what would truly solve the original problem before the conversation.
Pro tips
- Record yourself delivering the first 30 seconds, then paste a transcript back into the AI for critique. Spoken language often reveals hedging that written drafts hide. - Add a “no accidental negotiation” check. Ask the model to highlight phrases that make a final decision sound tentative. - Ask for a minimum viable handoff: the smallest set of documents and conversations that prevents operational harm. - Simulate the manager’s strongest reasonable questions, not a cartoon villain. Realistic pressure produces better rehearsal.
Prerequisites
Know whether you have accepted and cleared the new offer conditions you consider essential before resigning. Have the proposed last day, start date, current responsibilities, and any known notice expectations available. Write your private reasons for leaving and decide which of them you are willing to share. Review actual employment, benefits, equity, bonus, and policy documents yourself, and identify where professional advice may be needed.
Required tools
A general-purpose AI assistant with enough context capacity for the situation details and role-play. Voice mode can be helpful for spoken rehearsal but is not required. Use a secure note or document system for private reasons and transition information; avoid pasting confidential client, employee, security, or proprietary data into an AI service without authorization.
Frequently asked questions
Should I resign by email or in a meeting?
In many professional settings, the courteous pattern is a direct conversation followed by written confirmation, but your workplace, safety, location, and circumstances may make another approach more appropriate. The prompt can help you prepare either format, but it should not invent a universal rule. Check company policy and use judgment about whether a live conversation is safe and practical. The written notice should remain concise and should not become a detailed argument about why you are leaving.
What should I do if my manager demands an immediate answer to a counteroffer?
Return to the decision rule you set before the meeting. A short response such as “I appreciate that, and I do not make decisions like this on the spot” buys time without making a promise. If your decision is final, you can say so clearly rather than pretending to consider an offer you will not accept. The important work happened earlier: identifying which conditions could genuinely change your decision and which cannot.
How honest should I be about why I am leaving?
Be truthful, but do not confuse truthfulness with complete disclosure. Share reasons that are useful, proportionate, and consistent with the relationship you want afterward. Avoid turning the resignation into an unstructured performance review of the company or manager. If you offer feedback, make it specific and owned—what you experienced and needed—rather than a sweeping verdict about other people’s motives.
Can the AI write my resignation letter for me?
It can create a rehearsal draft and help you see the necessary components, but the final letter should be rewritten in your own words and checked for accuracy. A resignation is a durable employment record and may be read by people who later serve as references. Remove generic language you would never say, promises you cannot keep, and reasons you do not want documented. The useful role for AI is structure and critique, not impersonation.
What exit questions belong with HR or a lawyer?
Questions about coverage dates, final pay process, unused leave, retirement-plan administration, property return, and policy procedures often belong with HR or the relevant plan administrator. Contract interpretation, restrictive covenants, equity forfeiture, disputed compensation, or jurisdiction-specific obligations may require qualified legal or tax advice. The AI can help you organize the questions and documents, but it should not settle them. The source of truth is the actual document, plan, policy, agency, or professional responsible for the issue.
Recommended follow-up prompts
- Resignation Voice Audit: Review a draft for hedging, blame, generic AI phrasing, and promises that exceed the intended transition. - Counteroffer Red-Team: Argue the strongest case for staying, then test it against the original reasons for leaving and the Week 2 criteria. - Transition Risk Register: Identify the projects, access, decisions, and relationships most likely to fail after departure, then assign a handoff action to each.
Tags and categories
Tags:
resignation, counteroffer, transition plan, career communication, role-play, employee exit, job change
Categories:
Career Communication, Job Search Prompts
Citations
- U.S. Department of Labor, Protecting Retirement and Health Benefits after Job Loss: official guidance on health-coverage and retirement considerations when employment ends. - Internal Revenue Service, Retirement Topics—Termination of Employment: official overview of common options for an employer retirement-plan balance after leaving a job. - U.S. Department of Labor, Last Paycheck: federal law does not require an immediate final paycheck, while state requirements may differ—one reason not to let an AI state a universal rule. - Ketelsen.ai weekly template: per-variation section order, prompt presentation, diagnostic breakdown, examples, prerequisites, FAQs, and citation requirements.
The Complete Landing Package
Turn eight weeks of evidence into one controlled career transition.
The advanced failure is fragmentation. One document holds the offer analysis, another contains negotiation notes, the resignation plan lives in your head, and the onboarding plan begins after Day 1—when you are already flooded with names, acronyms, meetings, and expectations. A strong landing treats the transition as one connected system. The decision record explains what you accepted and why. The exit plan protects relationships and closes obligations. The first-90-days plan converts what you learned during the search into hypotheses, stakeholder questions, early wins, and review points. This prompt assembles those parts without allowing AI to invent facts, interpret contracts, or impersonate you.
Why this matters now
Onboarding is not merely an orientation checklist. Research on more than 10,000 Microsoft employees found that new hires continued building internal networks over time and still showed gaps from tenured employees after a six-month onboarding period, underscoring why stakeholder mapping cannot be treated as a first-week formality. Michael Watkins similarly frames successful transitions around accelerated learning, stakeholder relationships, early wins, and a longer-term destination. The first 90 days are therefore best designed as an evidence-gathering and relationship-building system, not a burst of performative productivity.
Act as my private career-transition analyst, red-team reviewer, and onboarding planner. You may structure, calculate, question, and rehearse. You may not make the decision for me, interpret legal documents, invent company facts, or ghostwrite words I present as my own.
Build one coherent landing package from candidate to established new hire.
INPUT PACKET A. My pre-offer criteria or Week 2 spec sheet: [PASTE] B. Final negotiated offer or Week 7 outcome: [PASTE VERIFIED TERMS] C. Interview dossier and company notes from Weeks 4 and 6: [PASTE] D. My reasons for leaving and counteroffer boundaries: [PASTE] E. Current-role transition obligations and key stakeholders: [PASTE] F. New-role job description, manager expectations, known team priorities, and start date: [PASTE] G. Personal constraints for the first 90 days: [TRAVEL, CAREGIVING, HEALTH, COMMUTE, LEARNING CURVE, OR OTHER]
DATA RULES
- Label every important item as verified fact, user judgment, assumption, or unknown.
- Never convert an assumption into a fact.
- Ask up to ten questions, ranked by how much each answer could change the decision, exit, or onboarding plan.
- Do not analyze confidential information I am not authorized to share.
PHASE 1 — FINAL DECISION RECORD 1. Rebuild my weighted decision matrix using my pre-offer criteria. Preserve my original weights unless I explicitly change them. 2. Check deal-breakers before calculating a total. 3. Show the evidence behind every score and mark uncertainty. 4. Run sensitivity tests: identify which one-point score changes or weight changes could flip the verdict. 5. Red-team the leading choice with the strongest reasonable case against it. 6. Produce a decision record containing the decision, rationale, unresolved risks, mitigations, and conditions I must confirm before acting.
Stop after Phase 1 and ask me to confirm my actual decision. Do not infer acceptance from the score.
PHASE 2 — EXIT OPERATING PLAN After I confirm the decision, create: 1. A resignation conversation outline in my voice profile: [DESCRIBE MY NORMAL TONE]. 2. A short written-notice rehearsal draft that I must rewrite before sending. 3. A counteroffer decision tree tied to my original reasons for leaving, including a no-answer-on-the-spot rule. 4. A transition map covering work products, owners, access, decisions, recurring obligations, risks, and stakeholder communications. 5. An exit-administration question list for HR, plan administrators, tax professionals, or legal counsel. Do not interpret employment contracts, restrictive covenants, equity terms, benefits rules, or notice law. 6. A final human-authorship pass that identifies generic phrases, unsupported claims, excessive detail, and language that does not sound like me.
PHASE 3 — 30/60/90-DAY ONBOARDING PLAN Build the plan around learning, relationships, delivery, and adaptation.
For Days 1-30, define:
- Questions to clarify success, scope, decision rights, communication norms, and constraints
- A stakeholder map with role, influence, knowledge, expectations, trust level, and next conversation
- A listening plan for my manager, peers, direct reports, customers, and hidden experts
- Systems, history, acronyms, and workflows to learn
- Two low-risk early-win candidates that create value without pretending I understand the organization too soon
For Days 31-60, define:
- Hypotheses to test about the team and role
- Relationships to deepen or repair
- One or two early wins to deliver, with owner, beneficiaries, evidence of success, and risk controls
- Decisions I should make, decisions I should influence, and decisions I should observe before acting
- A feedback cadence with my manager and key stakeholders
For Days 61-90, define:
- A durable operating rhythm
- A first-quarter results review against agreed expectations
- A stakeholder-network gap check
- Priorities to stop, continue, or scale
- A six-month direction statement that connects early learning to longer-term value
For every 30-day phase, include objectives, actions, evidence, dependencies, risks, and a scheduled review question. Treat dates as planning markers, not universal laws; adjust them to the role’s actual pace.
PHASE 4 — INTEGRATION AND HANDOFF 1. Trace how the decision criteria affect the exit and onboarding plans. Example: if manager quality was a top criterion, schedule explicit expectation and feedback conversations early. 2. Trace how interview evidence becomes onboarding hypotheses, not assumed truth. 3. Identify contradictions across my materials and ask me to resolve them. 4. Create a one-page weekly review checklist for the first 13 weeks. 5. Create a compact YAML appendix with these keys: decision, unresolved_risks, exit_milestones, stakeholders, early_wins, review_dates, and evidence_log. Use only facts and plans already established in the conversation. 6. End with a pre-mortem: imagine the transition failed after six months, list the five most plausible causes, the earliest warning sign for each, and one preventive action.
QUALITY GATES
- No invented statistics, company facts, people, policies, or legal conclusions.
- No recommendation may hide a deal-breaker behind a high total score.
- No early win may depend on authority, trust, or context I have not earned.
- No human-facing draft is final until I rewrite it in my own words and verify it is true.
- When evidence is thin, say unknown and propose a question or observation that would reduce uncertainty.
How the AI reads this prompt
Practical examples from different industries
An illustrative hospital operations director uses the full package after negotiating a role responsible for patient-flow improvement. Her Week 2 criteria prioritize executive sponsorship, staffing authority, mission fit, schedule sustainability, and data access. The decision audit reveals that data access remains verbal rather than documented, so she confirms it before resigning. Her onboarding plan treats interview claims about bottlenecks as hypotheses, maps clinical and administrative stakeholders, and selects an early win focused on clarifying escalation paths rather than redesigning workflows before earning trust.
An illustrative software engineering manager is moving from a mature enterprise to a venture-backed company. The advanced prompt links his top criterion—decision autonomy—to an early expectation-setting conversation with the founder, while the sensitivity analysis shows that the offer’s advantage depends heavily on the assumed value of equity. The exit plan protects active projects and access ownership without promising indefinite support. The first-90-days plan maps product, engineering, sales, and investor influence, then delays major architectural changes until he has observed the release process and tested the interview narrative against operating reality.
An illustrative museum education leader is leaving an organization she cares about for a role with more budget responsibility and community reach. Her decision record preserves a concern about board involvement instead of allowing title and mission language to overwhelm it. The resignation plan helps her communicate gratitude without apologizing for leaving, and the transition map protects school partnerships and grant deadlines. In the new role, the stakeholder map includes curators, educators, development staff, teachers, donors, and community partners, while early wins focus on listening and repairing a scheduling pain point rather than launching a high-profile program immediately.
Creative use case ideas
- Use the integration logic for an internal promotion, where the “exit” is a handoff from the old role rather than departure from the company. - Adapt the 13-week review system to a sabbatical return, military-to-civilian transition, fellowship, residency, or elected volunteer leadership role. - Turn the stakeholder map into a relationship-learning plan for joining a new neighborhood board, arts collective, or open-source project. - Use the pre-mortem before a major career pivot to identify which skills, relationships, or financial assumptions need protection. - Preserve the YAML handoff as a private transition log that future AI sessions can update without rereading the entire eight-week search history.
Adaptability tips
For individual-contributor roles, replace formal decision rights with sources of influence, review authority, and technical ownership. For executives, expand the stakeholder map to include board members, external partners, regulators, and informal power centers, and increase the emphasis on listening before early wins. For hourly, frontline, or shift-based roles, compress the plan into 2/4/8-week checkpoints if the learning cycle is faster. For a fully remote role, add explicit network-building, communication-channel, and documentation goals. For a role with a fixed probation period, align the review dates to the employer’s actual checkpoints without asking the AI to interpret the legal meaning of probation.
Pro tips
- Version the decision criteria, offer facts, and plan. Record what changed, who confirmed it, and when. - Ask the AI to produce an evidence log after each weekly review: observation, source, confidence, implication, and next test. - Use two red teams: one against the decision before resignation, and one against the onboarding plan after 30 days of real evidence. - Keep the machine-readable appendix deliberately small. State should preserve decisions and open loops, not every conversational detail.
Prerequisites
The strongest version uses artifacts from the whole series: Week 1’s baseline and initial decision criteria, Week 2’s spec sheet, Week 4’s company dossier, Week 6’s diagnostic interview reads, and Week 7’s negotiated outcome. A standalone reader can still use it by supplying a verified offer, personal priorities, interview notes, reasons for leaving, current-role obligations, and known new-role expectations. Set aside enough time to answer clarification questions and review each phase before moving to the next.
Required tools
A general-purpose AI assistant with a large context window and reliable multi-step instruction following. A document editor or private knowledge system is recommended for versioning the input packet, decision record, and weekly reviews. A spreadsheet can help verify scoring calculations, but the AI’s totals should still be checked manually. Calendar software is useful for scheduling stakeholder conversations and review dates after the user approves the plan.
Frequently asked questions
Do I need all eight weeks of artifacts to use this prompt?
No. The prompt includes a standalone path because many readers will arrive with an offer already in hand. The minimum viable packet is a verified offer, a written list of priorities, your reasons for leaving, interview notes, and what you know about the new role. The earlier artifacts improve traceability because they preserve criteria and observations before the final offer could influence them. Missing history should be labeled missing, not reconstructed as though it existed.
Why does the prompt stop after the decision phase?
Because analysis and authorization are different actions. A high score can support a recommendation, but it cannot accept an offer, trigger a resignation, or establish your real intent. The stop creates a control point where you inspect the evidence, resolve missing facts, and state the decision yourself. This is the same reason mature workflows require approval before a consequential next step.
Is a 30/60/90 plan too rigid for some roles?
Yes, if treated as a universal schedule. The periods are useful review markers, not laws of organizational life. A seasonal business, emergency role, startup, academic calendar, or regulated environment may require a different cadence. Keep the structure—learning, relationships, delivery, evidence, and review—but adapt the dates to the actual work.
How should I use interview notes without overtrusting them?
Treat them as leads to test. Interviewers may describe aspirations, partial views, or the part of the organization they know best, and candidates may hear what they hope to hear. Convert each important claim into a hypothesis with a source, confidence level, and observation or conversation that can confirm it. That preserves the value of the search intelligence without mistaking recruiting context for settled operating truth.
What belongs in the YAML appendix?
Only compact state that helps the next review continue without re-deriving the project: the decision, unresolved risks, exit milestones, stakeholders, early wins, review dates, and evidence log. Do not put sensitive documents, long transcripts, or confidential company data into the appendix. The goal is continuity, not surveillance or exhaustive memory. A small, well-maintained state file is more useful than a sprawling summary no one trusts.
Recommended follow-up prompts
- Week-One Evidence Log: Convert first-week observations into facts, hypotheses, contradictions, and next questions without rushing to conclusions. - Stakeholder Conversation Planner: Design a tailored purpose, questions, and follow-up for each person on the map, then rewrite the wording in your own voice. - 30-Day Plan Recalibration: Compare the original onboarding plan with real evidence, retire invalid assumptions, and revise the next 60 days.
Tags and categories
Tags:
30-60-90 plan, onboarding, stakeholder mapping, early wins, decision record, resignation, counteroffer, career transition, YAML handoff
Categories:
Career Systems, Advanced Job Search Prompts
Citations
- Microsoft Research, Large-Scale Analysis of New Employee Network Dynamics (The Web Conference 2023): study of network development among more than 10,000 new employees in remote and hybrid work. - Michael D. Watkins, Start Your New Leadership Role with the End in Mind (Harvard Business Review, 2023): connects early learning, stakeholder relationships, and early wins with longer-term transition goals. - Microsoft WorkLab, Strategies for Onboarding in a Hybrid World: emphasizes active manager involvement, early one-on-ones, expectation alignment, buddies, and network building. - Ketelsen.ai Week 8 theme: the advanced complete landing package, the eight-week artifact chain, legal boundaries, and the requirement that AI remain the analyst rather than the ghostwriter.
Which of the three should you use?
The beginner prompt is the right choice when the immediate problem is deciding whether the offer deserves a yes. It uses a small number of ranked priorities, a transparent scoring method, and a deliberate argument for both accepting and declining. Its strength is speed and auditability. It does not attempt to manage the entire transition; it prevents the first irreversible error by making the decision criteria visible before emotion takes over.
The intermediate prompt begins after the decision is substantially made. It is built for human pressure: the resignation conversation, the possibility of a counteroffer, the temptation to over-explain, and the practical work of leaving a team in usable condition. Its core technique is rehearsal with boundaries. The advanced prompt integrates the whole journey. It preserves prior criteria, inserts a human approval gate, builds the exit as an operating plan, converts interview intelligence into testable onboarding hypotheses, and creates a 13-week review system with structured state for continuity.
Choose based on the next failure you need to prevent. Use Beginner when the offer is distorting judgment. Use Intermediate when the decision is clear but the conversation and transition are not. Use Advanced when you have multiple artifacts, meaningful complexity, or a role important enough to justify a controlled handoff from candidate to new hire. The three can also be chained: score first, rehearse the exit second, then build the 90-day system after the decision is confirmed.
TAGS:
