WEEK 106 :: 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: "The Offer — Negotiating From Evidence, Not Anxiety."
This is Week 7 of an eight-week series on running a job search with AI — the negotiation week, and the emotional and financial peak of the series, exactly as it was in the car series. An offer is on the table. The reader's heart says grab it before they change their minds; six weeks of artifacts say otherwise. Employers broadly expect candidates to negotiate — yet first-timers routinely accept the opening number, and the cost of that compounds over a career the way a bad interest rate compounds over a loan: every future raise, bonus percentage, and next-job offer anchors on the number the reader accepts this week.
The reader is not walking in empty-handed. Week 1 set the compensation baseline. Week 2 wrote the deal-breakers. Week 4 built the company dossier. Week 6's interviews revealed how much they want this reader. Negotiation is where the whole series' evidence gets spent.
The deliverable the reader should walk away holding: a negotiation plan with a researched target range, a walk-away number, and scripted responses for the conversations and emails ahead.
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:
- Decode the total offer. Base, bonus, equity, benefits, and the fine print translated into real comparable dollars — vesting schedules that gate the money, bonus targets versus bonus reality, what the benefits actually replace — from the offer documents the reader supplies, ending in a one-page picture of what is actually being offered.
- Benchmark it against evidence the reader gathers. A research structure for building the market case: which pay-transparency postings, published salary data sources, and leveling comparisons to pull, how to weigh them for the reader's role, level, and metro, and how to assemble them into a defensible target range — the AI organizing evidence the reader collects, not asserting what the role pays.
- Script the negotiation itself. Word-for-word: the counter delivered with warmth and a number, the email version, responses to "that's the best we can do" and "what number would get you to yes," the scenario tree for competing offers — and the walk-away line the reader decides on in advance, when they are calm.
At the advanced tier, the strongest version of this week is the complete negotiation playbook — decoded offer, evidence-backed range, scenario tree with scripted branches, and competing-offer orchestration handled honestly (real timelines, no bluffing) — built so the reader can run the conversation from a page instead of from adrenaline.
The constraint that defines this week. AI models cannot see current market compensation, and a negotiation anchored on an invented number is worse than no research at all. No prompt may ask the AI to state what a role, level, or metro currently pays as fact, to value a specific company's equity, or to promise that a tactic will produce a result. The market case is built from sources the reader pulls — pay-transparency postings, published salary data, people in the role. Equity in a private company gets a framework for the questions to ask, never an AI-asserted valuation. And where an offer raises legal questions — non-competes, clawbacks, contract terms — the prompts point to a lawyer, not to the AI's reading. Scripts are coaching, not guarantees, and none of this is financial advice: the plan organizes the reader's decision; the decision stays theirs.
Design the prompts so the AI does what it is genuinely good at: decoding dense documents, structuring an evidence file, and drafting language the reader can rehearse and make their own. The reader supplies the offer, the market evidence, and the walk-away point; the AI supplies the decode, the structure, and the words to start from. "Word-for-word" means a complete starting draft, not a finished performance — and this is the week that rule matters most: the final pass belongs to the reader. A counter delivered in someone else's voice collapses at the first follow-up question, and the negotiation email lands on the desk of the exact hiring humans this series' contract is about. Every scripting prompt should end by handing the language back for the reader's own rewrite — rehearsed until it is genuinely theirs — and the post should say why.
Series dependency chain, for the Metadata block: Week 7 consumes Week 1's compensation baseline (the floor), Week 2's deal-breakers (what cannot be traded away), Week 4's company dossier (the other side's position), and Week 6's interview signals (how much they want this reader). Week 7 produces the negotiation plan and its outcome — consumed by Week 8, where the final numbers meet the final decision.
Because readers may arrive at this post with an offer in hand and none of the earlier artifacts, the prompts should work from the offer letter and the reader's own sense of their floor, while making clear the negotiation is strongest when it spends six weeks of accumulated evidence.
Three difficulty tiers as always — Beginner, Intermediate, Advanced — each a genuinely different approach to the same problem, not the same prompt at three lengths.
On examples: this is a career topic that touches every industry. The template lists tech startup / retail / freelance as suggested industry examples — those are marked MAY, and adapting them is expected here. A first-time negotiator with a single offer and sweaty palms, a reader weighing startup equity against a bigger base elsewhere, and one holding two offers on different timelines 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 — above all, no salary numbers. If a prompt or example needs a wage figure to work, restructure it so the reader's own researched number is the input.)
## 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: 7` 2. ☐ `## Lead` present once, at the very top, before Variation 1 3. ☐ `## In one line` present in all three variations 4. ☐ `## What this prompt gives you` present in all three variations 5. ☐ `## The Prompt` present in all three variations, with the prompt in double quotes beneath it 6. ☐ `## Introductory Hook` and `## Current Use` present in all three variations (three of each — not one) 7. ☐ Every template heading written as `##`, none bolded instead; prompt breakdown is running text split on ` : `, with no `###` headings inside it
A complete post has 57 `##` headings. If your count is well short, a section is missing or was bolded instead of hashed.
One extra check this week: confirm no prompt asks the AI to state current compensation for a role or metro as fact, value a specific company's equity, promise a negotiation outcome, or interpret contract terms that belong with a lawyer. The market case is built from evidence the reader gathers; the walk-away number is the reader's own. Also confirm every negotiation script and email prompt ends with the reader rewriting and owning the final words (the series contract's final-pass rule) — a counter in someone else's voice collapses at the first follow-up.
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 offer can turn six weeks of careful preparation into six minutes of anxious decision-making. This week’s three prompts prevent that collapse: a beginner offer decoder and first-counter coach, an intermediate evidence-weighting system, and an advanced negotiation playbook with scripts, decision gates, and honest competing-offer branches. The goal is not to make AI negotiate for you. It is to enter the conversation knowing what the offer contains, what your evidence supports, what you will ask for, and where you will stop.
The Calm First Counter
Turn an offer into one clear picture and a calm counter.
The hardest part of receiving an offer is that excitement and uncertainty arrive in the same envelope. The headline number gets all the attention, while bonus conditions, benefit costs, vesting schedules, review timing, and restrictive language hide in the margins. A first-time negotiator may accept quickly not because the offer is right, but because the document feels too complicated to challenge. This prompt slows the moment down. It helps the reader separate confirmed value from conditional value, identify unanswered questions, choose a personally meaningful target, and prepare a simple counter without pretending the AI knows what the market currently pays.
Why this matters now
This prompt matters when an offer has just arrived and the reader needs clarity before confidence. It works even without the artifacts from earlier weeks, provided the reader can supply the offer and a personal minimum they are willing to accept. The AI acts as a private analyst and rehearsal partner: it organizes what is known, refuses to invent missing numbers, and creates language the reader can revise. That distinction matters because the hiring manager must ultimately hear a real person making a decision they understand and can defend.
You are my private job-offer analyst and negotiation coach, not my ghostwriter.
I will provide: 1. The offer letter or a summary of the offer. 2. Any benefits information I have. 3. My personal minimum acceptable outcome, if I know it. 4. Any priorities or deal-breakers that matter to me. 5. Any compensation evidence I have already collected.
Your job is to help me understand the offer and prepare for a first negotiation conversation.
First, separate everything I provide into three groups:
- Confirmed offer terms.
- Conditional, unclear, or incomplete terms.
- Questions I should ask before deciding.
Then create a one-page offer picture covering:
- Base compensation.
- Bonus or incentive compensation, including conditions.
- Equity or long-term incentives, including vesting or access restrictions.
- Signing or relocation support.
- Benefits and time off.
- Review timing and promotion or compensation-review timing.
- Any clauses or obligations that require closer attention.
- What appears to be first-year value versus recurring value.
Do not guess missing amounts. Do not state what this role, level, company, or metro currently pays unless I provide the evidence. Do not assign a value to private-company equity. Do not interpret non-competes, clawbacks, intellectual-property clauses, or other legal terms; flag those for review by a qualified lawyer.
Ask me no more than five focused questions needed to complete the analysis.
After I answer, help me choose:
- My preferred target.
- My acceptable outcome.
- My walk-away point.
These numbers must come from my own evidence, priorities, and financial needs. If I have not supplied enough information to choose them responsibly, tell me what I still need to research.
Finally, draft: 1. A warm spoken counter of no more than four sentences. 2. A short negotiation email. 3. A response to: ‘This is the best we can do.’ 4. A response to: ‘What number would get you to yes?’
Keep the language direct, appreciative, and specific. Do not bluff, threaten, or invent competing offers. Label every script as a starting draft.
End by asking me to rewrite the scripts in my own words and rehearse them aloud until I can explain every request naturally without reading from the page.
How the AI reads this prompt
Practical examples from different industries
A first-time healthcare administrator receives a single offer after a long search and feels pressure to accept immediately. They paste the offer, benefits summary, personal minimum, and notes from the interview process into the prompt. The AI separates guaranteed compensation from a conditional bonus, identifies unanswered questions about review timing and health-plan costs, and produces a one-page summary. It then creates a simple counter based only on the administrator’s stated target. The value is not aggressive bargaining; it is replacing a vague emotional reaction with a calm sequence of questions and decisions.
A manufacturing supervisor is moving from hourly work into a salaried leadership role. The offer includes base compensation, a performance incentive, additional responsibility, and a benefits package that is difficult to compare with the supervisor’s current arrangement. The prompt helps distinguish recurring compensation from conditional compensation and flags missing information about overtime expectations, scheduling, and the first compensation review. The resulting conversation script gives the supervisor a respectful way to ask for clarification and make one evidence-supported request without pretending to know market data they have not gathered.
A museum program coordinator receives an offer for a role they genuinely want, but the base compensation is close to their minimum and the time-off policy is less flexible than expected. They use the prompt to organize the offer and identify which terms matter most. Rather than treating negotiation as a single demand for more money, the output helps them prepare alternatives involving start date, professional-development support, review timing, and time off. The reader still decides what matters, but the prompt makes the available tradeoffs visible before the conversation begins.
Creative use case ideas
- Use the offer picture to explain a career decision to a spouse or trusted adviser without forwarding the entire offer packet. - Convert the unanswered-question list into an agenda for a recruiter call. - Compare a promotion offer with the reader’s current position, even when no company change is involved. - Rehearse the conversation with a friend who plays the hiring manager and interrupts with realistic objections. - Adapt the framework for a graduate assistantship, fellowship, residency, apprenticeship, or creative commission.
Adaptability tips
The prompt can be shortened when the offer is simple. Remove sections for equity, relocation, or bonuses when they do not apply, but retain the distinction between confirmed and conditional terms.
Readers who completed earlier weeks should paste in their compensation baseline, deal-breakers, company dossier, and interview signals. Those artifacts give the AI better context without allowing it to invent a market conclusion.
The output can also be adapted around the reader’s main concern. Someone focused on cash can emphasize base, bonus reliability, and review timing. Someone focused on family logistics can elevate schedule, leave, travel, insurance, and start-date flexibility. The structure stays the same; the decision weights change.
For nontraditional arrangements, replace “offer letter” with the actual source document: a promotion memo, contract summary, fellowship notice, grant terms, or project agreement. Legal interpretation still belongs with a qualified professional.
Pro tips
Ask the AI to mark every item as guaranteed, conditional, discretionary, estimated, or unknown. This prevents different kinds of value from being added together as though they were equally certain.
Request a “questions before countering” checkpoint. Some offers should be clarified before the reader names a number, especially when the bonus formula, level, working arrangement, or review schedule is incomplete.
Rehearse the spoken script twice: once with a cooperative recruiter and once with a rushed or resistant recruiter. The second version exposes language that depends too heavily on a friendly response.
Prerequisites
The reader needs the offer letter or a reliable summary of its terms. A benefits summary is helpful but not required for the first pass.
The reader should know at least a provisional personal minimum. This is not necessarily a market benchmark; it is the lowest outcome they can responsibly accept after considering their needs, alternatives, and priorities.
Any compensation research already gathered should be included as source material. The AI should not be asked to replace missing current research with its own unsupported estimate.
Required tools
Any general-purpose AI assistant capable of analyzing pasted text is sufficient. A document-capable version is useful when the reader wants to upload an offer letter or benefits summary directly.
Before uploading documents, remove unnecessary personal identifiers, signatures, account information, and other sensitive data. Do not upload confidential material unless the tool and account configuration are appropriate for that material.
A calculator or spreadsheet may help verify totals, but it is not required for the basic prompt.
Frequently asked questions
Should I use this prompt before acknowledging the offer?
A prompt should not delay a courteous acknowledgment. The reader can thank the employer, confirm receipt, and ask when a response is needed without accepting or negotiating immediately. The analysis can then happen before the substantive conversation. The important distinction is between acknowledging the offer and agreeing to it.
What if I do not have salary research yet?
The prompt can still decode the offer and identify missing information. It should not invent a target range or claim the offer is above or below market without reader-supplied evidence. The reader can use the unanswered-question list to begin collecting pay-transparency postings, published data, and relevant comparisons. A temporary personal floor may guide timing, but it is not a substitute for a researched market case.
Can I paste the AI-generated email directly into my reply?
That is a poor default. The draft should be treated as scaffolding: keep the structure, verify every claim, and replace the phrasing with language the reader would naturally use. The final email must be true, specific, and personally owned. Reading it aloud is a useful test; anything that feels difficult to say will usually feel artificial to receive.
What if the employer says the offer is non-negotiable?
First determine whether the statement applies to base compensation, the entire package, or only one component. The reader can ask whether other terms have flexibility, such as review timing, start date, time off, signing support, schedule, or professional development. The prompt can help organize alternatives, but it cannot promise that flexibility exists. A genuine walk-away point remains valuable even when the answer is no.
Can this prompt tell me whether a contract clause is enforceable?
No. It can identify clauses that deserve attention and help the reader prepare questions, but enforceability depends on law, jurisdiction, facts, and the wording of the agreement. Non-competes, repayment obligations, clawbacks, intellectual-property provisions, and similar terms should be reviewed by a qualified lawyer when they materially affect the decision. The AI’s role is issue spotting, not legal interpretation.
Recommended follow-up prompts
- “Build me a research checklist for collecting current compensation evidence without asking you to supply the salary numbers.” - “Role-play the recruiter’s response to my counter and interrupt me with realistic follow-up questions.” - “Create a final-decision worksheet that compares the negotiated outcome with my compensation baseline and deal-breakers.”
Tags and categories
Tags:
job offer, salary negotiation, total compensation, offer letter, counteroffer, negotiation script, career planning
Categories:
Job Search, Prompt Engineering
Citations
NOT APPLICABLE
The Evidence-Backed Market Case
Build a defensible range from evidence you gather and weight.
Negotiation advice often jumps from “research your worth” to “ask confidently,” leaving the difficult part unexplained. A reader may collect six job postings, two salary websites, one recruiter comment, and a conversation with a former colleague—then have no method for deciding which evidence deserves the most weight. This prompt turns a pile of sources into an auditable market case. The AI does not announce what the role pays. It organizes evidence the reader supplies, challenges weak comparisons, calculates ranges transparently, and helps convert the strongest facts into a concise negotiation thesis the reader can defend.
Why this matters now
Compensation information is abundant but uneven. A posted range may cover several levels, a broad geography, or a different mix of responsibilities. A salary-data page may be current yet too general for the specific role. The intermediate prompt matters because it asks the AI to evaluate relevance rather than merely summarize numbers. It also prevents the reader from cherry-picking only the highest figures, producing a case that remains credible when the recruiter asks how the target was chosen.
You are my private compensation-evidence analyst and negotiation coach. You are not a source of current salary facts, and you are not my ghostwriter.
I will provide:
- The complete offer or a structured summary.
- The role title, responsibilities, level, location, and working arrangement.
- My compensation baseline and personal floor.
- My non-negotiable terms and preferred tradeoffs.
- Evidence I have collected, such as pay-transparency job postings, published salary data, recruiter information, professional-association material, or notes from people familiar with the role.
- Relevant interview signals and company information.
- Any deadlines or competing-offer timelines.
Do not add compensation figures from memory. Use only the evidence I supply. If the evidence is insufficient, tell me exactly what additional comparison I should collect.
Create an evidence ledger. For every source, record: 1. Source type and date. 2. Role and level match. 3. Responsibility match. 4. Location and working-arrangement match. 5. Company-size or industry match when relevant. 6. Whether the figure represents base, cash compensation, or total compensation. 7. Important limitations. 8. A relevance rating of High, Medium, or Low, with an explanation.
Next, identify duplicates or sources that may be repeating the same underlying data. Do not treat repeated numbers as independent confirmation unless the sources are genuinely independent.
Using only High- and Medium-relevance evidence, build:
- A defensible market range.
- A preferred target.
- An acceptable outcome.
- A walk-away point supplied or approved by me.
- A clear explanation of how each was derived.
- A sensitivity check showing how the conclusion changes if weak or extreme evidence is removed.
Then decode the offer against that evidence:
- Where the offer falls within the reader-supplied range.
- Which components are guaranteed, conditional, discretionary, or unknown.
- What is first-year-only versus recurring.
- Which gaps matter most to my priorities.
- Which non-cash terms could be reasonable trade options.
For private-company equity, do not estimate value. Create a question list covering ownership percentage or share count context, security type, vesting, exercise requirements, liquidity conditions, dilution, expiration, and access to supporting documents.
For legal clauses, flag the issue and recommend qualified legal review. Do not interpret enforceability or provide legal advice.
Create a negotiation brief containing: 1. A three-sentence evidence-based case. 2. My opening request and rationale. 3. My concession ladder, with items I may trade and items I will not trade. 4. A spoken counter. 5. An email draft. 6. Responses to:
- ‘That number is outside our range.’
- ‘This is the best we can do.’
- ‘What number would get you to yes?’
- ‘We need an answer today.’
<!-- end list -->
7. A pause line I can use when I need time to think.
Keep every statement accurate to my evidence. Do not bluff about other offers, deadlines, or willingness to walk away. Label the scripts as rehearsal drafts.
Finish with a credibility audit:
- Which claims are strongly supported?
- Which claims are weak?
- What could the employer reasonably challenge?
- What should I remove rather than overstate?
Then ask me to rewrite the final spoken and written language in my own voice, verify every factual claim, and rehearse the branches until I can respond without reading.
How the AI reads this prompt
Practical examples from different industries
A cybersecurity professional receives an offer whose title matches several public postings, but the responsibilities appear broader than the title suggests. The reader gathers current pay-transparency listings for comparable responsibilities, not merely identical titles, and adds a published salary source plus notes from two professional contacts. The prompt rates the sources, identifies one posting as a poor location match, and warns that two salary pages may rely on overlapping data. The resulting market case is narrower, more credible, and easier to explain than simply choosing the highest number found online.
A nonprofit development director is considering an offer with modest base compensation, a performance incentive, strong leave, and meaningful flexibility. The reader’s evidence includes nonprofit postings, association material, and comparable roles with different fundraising scopes. The prompt separates organizations by budget and responsibility match, preventing a large-institution role from dominating the comparison. It then helps the reader decide whether to prioritize base compensation, an earlier review, additional leave, or schedule flexibility. The output respects the mission-driven context without treating goodwill as a substitute for evidence.
A logistics manager has two possible career paths: a larger established employer with a stronger cash package and a smaller company offering broader responsibility and private-company equity. The prompt evaluates the reader-supplied compensation evidence for each role separately rather than pretending the titles are interchangeable. It refuses to assign a value to the private equity and instead generates a due-diligence question list. The negotiation brief focuses on guaranteed compensation, decision timelines, role scope, and the conditions under which the reader would accept uncertainty.
Creative use case ideas
- Build an evidence file for an internal promotion when the employer has not issued a formal external posting. - Compare a salaried role with contract or freelance work by separating guaranteed compensation from variable revenue and self-funded benefits. - Help a graduating student distinguish entry-level evidence from postings that quietly require several years of experience. - Prepare a community-college instructor for a department-chair stipend or expanded-duty discussion. - Audit a compensation case after a rejected counter to determine whether the evidence, request, or delivery needs improvement.
Adaptability tips
Readers with limited evidence can use the ledger before using the negotiation sections. The prompt will reveal which missing comparison would most improve the analysis, allowing targeted research instead of endless browsing.
The relevance criteria can be changed for the role. A highly regulated position may place more weight on credentials and responsibility. A remote role may require careful treatment of geographic pay policies. A sales role may need stronger separation between base, target incentives, quota design, and actual attainment information supplied by the reader.
The same structure can compare an external offer with an internal retention proposal. Label each package separately and prevent benefits, incentives, or one-time payments from being combined unless they are defined consistently.
For international or cross-border offers, add currency, tax residency, benefit portability, and employment-status questions. The AI can organize those issues but should not provide tax, immigration, financial, or legal conclusions.
Readers who dislike numerical scoring can retain High, Medium, and Low relevance labels. Readers who prefer more formal analysis can request a documented weighting method, provided the weights remain visible and adjustable.
Pro tips
Ask the AI to produce an “evidence exclusion log” listing every source it did not use and why. This makes selective reasoning visible and helps the reader defend the process.
Separate the target range from the opening request. A negotiation opening can account for expected movement, but the prompt should never hide the difference between an evidence-supported range and a strategic request.
Ask for the strongest employer-side interpretation of the evidence. A fair opposing case is more useful than an exaggerated objection because it exposes the claims most likely to matter in a real conversation.
Save the evidence ledger with dates and source links. If the process extends over several weeks, the reader can update individual entries without rebuilding the entire market case.
Prerequisites
The reader needs a structured summary of the offer and a meaningful set of compensation evidence they collected themselves. A small number of strong comparisons is preferable to a large pile of poorly matched sources.
The role’s responsibilities, level, location, and working arrangement should be described clearly. Titles alone are not sufficient for dependable comparison.
The reader should identify personal priorities, acceptable tradeoffs, and deal-breakers before asking the AI to build a concession ladder. Earlier series artifacts are ideal, but a fresh written list will work.
Any competing offer or deadline must be real and accurately described.
Required tools
A general-purpose AI assistant with sufficient context capacity to analyze several job postings or evidence summaries is recommended. Document upload is useful but not essential if the evidence is organized in text.
A spreadsheet is strongly recommended for the evidence ledger, especially when comparing several sources. The reader should retain source dates, links, quoted ranges, and notes outside the AI conversation.
A calculator may be used to verify range calculations and first-year versus recurring compensation. Sensitive or confidential information should be removed before uploading.
Frequently asked questions
How many salary sources do I need?
There is no fixed number that guarantees a reliable conclusion. Relevance, independence, recency, and comparability matter more than volume. Several closely matched sources may be more useful than dozens of generic estimates. The prompt should tell the reader when the evidence remains too thin rather than manufacturing certainty.
Should I use the highest number I find as my target?
Not automatically. An extreme figure may come from a broader role, a higher level, a different location, or an unusual employer. The evidence ledger exists to expose those differences before a target is chosen. A credible request is one the reader can explain without hiding the limitations of the comparison.
What if different sources disagree substantially?
Disagreement is information. The prompt should examine whether the sources measure different compensation components, job levels, locations, industries, or dates. It may be appropriate to create separate clusters rather than force everything into one range. The reader should not average fundamentally different comparisons merely because they contain numbers.
Can the AI search for the evidence for me?
The safer design is for the reader to collect and verify the sources, then give them to the AI for organization and analysis. An AI with browsing access may help identify possible sources, but the reader should open them, confirm their dates and contents, and preserve the links. The final range should be traceable to evidence the reader actually reviewed.
What if the employer challenges my sources?
The reader should avoid turning the conversation into a courtroom presentation. A concise explanation of the best-matched evidence is usually stronger than listing every source. The prompt’s credibility audit helps remove weak claims before the conversation. The market case supports the request, but the request can also include the reader’s experience, role scope, and demonstrated fit when those points are true.
Recommended follow-up prompts
- “Challenge my compensation evidence as a skeptical recruiter and identify every weak comparison.” - “Turn my approved target and concession ladder into a live negotiation rehearsal with branching responses.” - “Update my Week 1 compensation baseline using only the final negotiated terms I confirm.”
Tags and categories
Tags:
compensation research, salary evidence, pay transparency, market range, offer comparison, concession planning, negotiation strategy
Categories:
Job Search, Research and Analysis
Citations
NOT APPLICABLE
The Complete Negotiation Playbook
Run the entire negotiation from a page, not adrenaline.
A complex offer negotiation is not one conversation. It is a sequence of decisions made across email, phone calls, internal approvals, deadlines, competing opportunities, and changing information. The danger is not only asking for too little. It is losing track of what was promised, conceding without a plan, misrepresenting another offer, or making a major decision while emotionally flooded. This advanced prompt builds an operating system for the negotiation: a decoded offer, an evidence ledger, a ranked issue list, a concession architecture, a scenario tree, rehearsal scripts, and explicit decision gates. The reader remains the decision-maker and the only person who speaks for them.
Why this matters now
The advanced prompt is designed for offers with several moving parts or meaningful consequences. It is especially useful when the package includes incentives, equity, relocation, unusual terms, competing timelines, or several negotiable priorities. Rather than producing a single counteroffer, the AI helps the reader plan the negotiation as a controlled process. Every branch is tied to verified evidence and preapproved choices, reducing the chance that urgency, flattery, disappointment, or fear will rewrite the strategy in real time.
You are my private negotiation strategist, compensation analyst, red-team reviewer, and rehearsal partner. You do not make the decision for me, communicate with the employer, invent market facts, or ghostwrite my final words.
I will provide as many of the following as I have:
- The offer letter and benefits materials.
- My Week 1 compensation baseline or current personal floor.
- My Week 2 deal-breakers and preferred tradeoffs.
- My Week 4 company dossier.
- My Week 6 interview signals and notes.
- My reader-verified compensation evidence.
- My career priorities and risk tolerance.
- Any real competing offers, interview processes, and deadlines.
- Relevant household, relocation, timing, or transition constraints.
- Questions I need a lawyer, tax professional, or financial professional to review.
Operate in phases. Stop at the end of each phase and ask me to approve or correct the work before continuing.
PHASE 1 — SOURCE AND CLAIM CONTROL
Create a source register for every document, figure, deadline, and claim I provide.
Label each item:
- Confirmed.
- Reader estimate.
- Employer statement.
- External evidence.
- Assumption.
- Unknown.
Do not convert an estimate or verbal statement into a confirmed term. Identify contradictions, stale information, missing documents, and claims that need verification.
PHASE 2 — OFFER DECODE
Build a complete offer model separating:
- Guaranteed recurring compensation.
- Conditional recurring compensation.
- First-year-only compensation.
- Long-term incentives.
- Benefits and time off.
- Work-location and schedule terms.
- Review and promotion timing.
- Relocation or transition support.
- Repayment, clawback, restrictive, intellectual-property, or termination-related provisions.
- Unknown or discretionary components.
Show calculations and assumptions. Never fill a blank with an invented number.
Do not estimate the value of private-company equity. Instead, build an equity-information request covering security type, number of shares or units, fully diluted context if available, vesting, cliff, exercise price, exercise window, expiration, dilution, liquidity conditions, repurchase rights, tax questions for a professional, and access to governing documents.
Flag legal, tax, investment, or financial questions for qualified professionals. Do not answer them as fact.
PHASE 3 — EVIDENCE MODEL
Using only compensation evidence I supplied and verified:
- Create a provenance-preserving evidence ledger.
- Rate role, level, responsibility, location, working-arrangement, industry, and company-context matches.
- Identify duplicated or dependent sources.
- Separate base compensation from cash compensation and total compensation.
- Exclude weak comparisons from the primary range.
- Build a defensible range and show the calculation.
- Run a sensitivity analysis without the highest, lowest, and weakest evidence.
- State the limits of the conclusion.
Do not state that a role or metro pays a particular amount beyond what my supplied evidence supports.
PHASE 4 — DECISION ARCHITECTURE
Help me define and approve:
- Ideal outcome.
- Strong acceptable outcome.
- Minimum acceptable outcome.
- Walk-away point.
- Terms that cannot be traded.
- Terms I can trade.
- Terms I can request if base compensation cannot move.
- The maximum uncertainty I am willing to accept.
- Conditions that require professional advice before acceptance.
Do not choose my walk-away point for me. Ask questions until I choose it.
Create a concession ladder. For each possible concession, record:
- What I would give.
- What I would request in return.
- Why the trade is acceptable.
- Whether the concession changes my decision.
- Whether it must be documented in writing.
PHASE 5 — NEGOTIATION STRATEGY
Create: 1. A one-paragraph negotiation thesis. 2. A prioritized request list. 3. The opening request. 4. The evidence supporting each request. 5. The order in which issues should be raised. 6. What should be discussed live versus confirmed by email. 7. A list of questions that should be answered before I counter. 8. A timeline based only on real deadlines. 9. A recordkeeping plan for promises and revisions.
For competing opportunities, use only truthful information. Never recommend inventing an offer, exaggerating interest, or creating a false deadline.
PHASE 6 — SCENARIO TREE
Build a branching scenario tree for:
- The employer accepts.
- The employer improves part of the offer.
- The employer says base compensation cannot move.
- The employer offers a one-time payment instead of recurring compensation.
- The employer asks for my exact acceptance number.
- The employer requests an immediate answer.
- The employer says the offer is final.
- The employer changes a nonfinancial term.
- The employer withdraws or threatens to withdraw.
- A real competing offer arrives.
- A competing process needs more time.
- The timelines cannot be aligned.
- New contract language appears.
- I become uncertain or emotionally activated during the conversation.
For every branch, provide:
- The objective.
- The facts I should verify.
- A short response draft.
- A question to ask.
- A pause or exit line.
- The decision gate that determines the next action.
- What must be documented afterward.
PHASE 7 — SCRIPT PACK
Draft starting language for:
- Opening a live negotiation.
- Making the counter with warmth and a specific request.
- Explaining the evidence without lecturing.
- Asking for flexibility across several components.
- Responding to ‘That is outside our range.’
- Responding to ‘This is the best we can do.’
- Responding to ‘What number gets you to yes?’
- Asking for time without sounding evasive.
- Coordinating two real offer timelines honestly.
- Declining without burning the relationship.
- Accepting conditionally while confirming revised terms.
- Accepting after all final terms are documented.
- Requesting written confirmation after a verbal agreement.
The scripts must be concise, truthful, and consistent with my approved decision architecture. Mark every script as a rehearsal draft.
PHASE 8 — RED TEAM
Act as:
- A skeptical recruiter.
- A compensation leader protecting internal equity.
- A hiring manager who wants me but has limited authority.
- A cautious adviser protecting me from an emotional decision.
For each perspective, identify:
- The strongest objection to my request.
- The weakest part of my evidence.
- Any inconsistency in my position.
- Any request that may be difficult to justify.
- Any sign that I am bluffing, oversharing, or negotiating against myself.
- How to improve the plan without becoming misleading or adversarial.
PHASE 9 — LIVE REHEARSAL
Run three simulations: 1. Cooperative recruiter. 2. Constrained but respectful recruiter. 3. Pressured conversation with resistance and deadlines.
During each simulation, respond only as the employer. Make me answer in my own words. Interrupt with realistic follow-up questions. After each round, score my response for clarity, accuracy, warmth, brevity, and consistency with my approved plan.
Do not reward aggressive language or unsupported certainty.
PHASE 10 — FINAL HUMAN-OWNED PLAYBOOK
Produce a compact negotiation playbook containing:
- Verified offer snapshot.
- Evidence-backed target range.
- Approved request.
- Concession ladder.
- Walk-away point.
- Scenario tree.
- Personal scripts rewritten by me.
- Questions awaiting answers.
- Professional-review items.
- Real deadlines.
- Written-confirmation checklist.
- Final accept, continue, pause, or decline decision gate.
Do not place AI-written language into the final script section until I rewrite and approve it.
End by requiring me to: 1. Verify every number, term, and deadline. 2. Obtain professional advice where needed. 3. Rewrite every employer-facing sentence in my own voice. 4. Rehearse without reading. 5. Make the final decision myself.
How the AI reads this prompt
Practical examples from different industries
A product leader is weighing an established-company offer against a startup opportunity. One package emphasizes predictable cash and formal benefits; the other includes broader scope, a smaller guaranteed component, and private-company equity. The reader supplies both offers, verified market evidence, real deadlines, and personal priorities. The playbook refuses to assign a speculative value to the startup equity. Instead, it builds separate offer models, creates an equity-information request, maps honest timeline conversations, and establishes decision gates based on the reader’s tolerance for uncertainty.
A physician practice administrator receives an offer involving base compensation, a performance component, relocation assistance, a repayment obligation, and restrictive contract language. The advanced prompt separates the business terms from issues requiring legal review and prevents the AI from declaring whether a clause is enforceable. It creates a list for counsel, a record of which terms are unresolved, and a scenario branch for receiving revised language late in the process. The reader gains a coordinated plan without confusing AI issue spotting with professional advice.
A university technology manager has one written offer and another employer moving toward a final decision on a different timeline. The manager does not want to mislead either organization or lose both opportunities through poor timing. The prompt builds an honest competing-process strategy using only actual dates and communications. It drafts starting language for requesting clarity, asking for reasonable time, and updating each organization without claiming an offer that does not exist. The scenario tree also includes what to do when the timelines cannot be aligned.
Creative use case ideas
- Prepare for a retention negotiation after announcing an intended departure, while keeping the external offer and internal proposal separate. - Build a negotiation playbook for a senior academic appointment involving research support, teaching load, laboratory resources, and partner considerations. - Adapt the scenario tree for a publishing contract, artistic residency, grant-supported position, or professional sports coaching role. - Create a post-negotiation audit showing which evidence changed the outcome and which assumptions were wrong. - Use the rehearsal engine to train a trusted mentor to challenge the reader’s plan from the employer’s perspective.
Adaptability tips
The ten phases can be reduced for less complex offers. A reader may use only source control, offer decode, decision architecture, scripts, and rehearsal. The phased design is modular; complexity should match the decision.
For executive or leadership roles, add governance, severance, change-of-control, incentive definitions, performance authority, public-disclosure considerations, and professional-review checkpoints. The AI should organize questions, not substitute for counsel or specialized advisers.
For unionized, public-sector, academic, residency, or fellowship positions, replace assumptions about individual flexibility with the applicable constraints the reader supplies. The scenario tree can still identify what is fixed, what requires approval, and what alternative terms may exist.
For multiple offers, create a separate source register and offer model for each organization before comparison. Combining documents too early creates attribution errors and can cause a term from one employer to appear in the other package.
For a promotion or retention case, replace external-market urgency with internal evidence: expanded responsibility, documented outcomes, level expectations, and the employer’s written proposal. Current compensation evidence must still come from reader-verified sources.
Pro tips
Maintain a negotiation change log. After every conversation, record the date, participants, statements made, unresolved questions, revised terms, and documents expected. This reduces reliance on memory and makes discrepancies easier to catch.
Ask the AI to identify irreversible decisions. Accepting, declining, resigning, relocating, exercising equity, or signing restrictive terms may have consequences that deserve a separate pause and verification checkpoint.
Use a “minimum necessary disclosure” review. The reader should share enough evidence to support the request without revealing personal financial pressure, confidential information, or details about another employer that should remain private.
After the negotiation, run a retrospective before Week 8. Record which terms changed, which did not, what the final package actually contains, and whether the result still meets the reader’s approved decision architecture.
Prerequisites
The reader should have the written offer and as many supporting documents as possible. Verbal descriptions should be clearly labeled and later confirmed in writing.
A reader-verified compensation evidence file is required for an evidence-backed range. The prompt must not be used to manufacture current compensation data.
The reader should identify a provisional floor, priorities, deal-breakers, and acceptable tradeoffs. The advanced process will refine them, but it cannot responsibly create personal values from nothing.
Real competing-offer details and deadlines must be documented accurately. Any legal, tax, investment, immigration, or financial issues should be separated for qualified professional review.
The full series works best when the reader supplies Week 1’s baseline, Week 2’s deal-breakers, Week 4’s company dossier, and Week 6’s interview signals.
Required tools
A general-purpose AI assistant with long-context support is recommended because the workflow may involve several documents, evidence entries, and scenario branches.
A spreadsheet or structured note system is recommended for the evidence ledger, offer model, concession ladder, and change log. These records should remain accessible outside a single AI session.
A calculator may be needed to verify totals and recurring-versus-one-time compensation. Document comparison software may help identify changes between original and revised offers.
Qualified legal, tax, financial, investment, or immigration professionals may be required depending on the terms. The AI must not be treated as a substitute.
Frequently asked questions
Is this process excessive for an ordinary job offer?
For a simple offer with few negotiable components, the entire ten-phase workflow may be unnecessary. The strength of the advanced prompt is modularity: the reader can use only the phases that reduce meaningful uncertainty. A short process is appropriate when the terms are clear and the decision is low complexity. More structure becomes valuable when the offer includes several compensation forms, unusual obligations, competing timelines, or major personal consequences.
Will a scenario tree make me sound robotic?
It will if the reader memorizes generated sentences without understanding them. The tree is meant to prepare decisions and conversational intentions, not dictate a theatrical performance. Each branch should be rewritten into the reader’s natural vocabulary and rehearsed with interruptions. The best result sounds spontaneous because the reasoning was prepared, not because every word was memorized.
What should I do when the employer introduces a new term during the call?
Do not force an immediate answer merely because the scenario was not anticipated. Use the pause line, restate what you heard, and ask for the revised term in writing. Then return to source control, update the offer model, and determine whether the change crosses a decision gate. New information should reenter the workflow rather than being handled from adrenaline.
Can the playbook decide between two offers?
It can make the differences, assumptions, and consequences visible. It can also test whether each offer meets the reader’s stated priorities and walk-away conditions. It should not choose which values matter most or make the final decision. Week 8 is where the confirmed final terms meet the reader’s final decision framework.
What happens if the employer withdraws the offer after I counter?
No prompt can guarantee that an offer will remain open. The scenario tree should prepare a calm response, preserve the relationship where possible, and prevent the reader from making unsupported claims in panic. Before negotiating, the reader must decide whether the potential improvement is worth the uncertainty involved. That risk assessment belongs to the reader, informed by the employer’s signals and the reader’s alternatives.
Recommended follow-up prompts
- “Convert the final negotiated terms into a clean Week 8 decision packet, preserving every source and unresolved assumption.” - “Run a final contradiction check across the original offer, revised offer, recruiter emails, and my negotiation notes.” - “Help me conduct a negotiation retrospective and update my reusable offer-playbook template.”
Tags and categories
Tags:
negotiation playbook, job offer strategy, scenario planning, competing offers, compensation analysis, decision gates, negotiation rehearsal
Categories:
Job Search, Advanced Prompt Systems
Citations
NOT APPLICABLE
Which of the three should you use?
The beginner prompt is the fastest route from emotional overload to a usable first conversation. It focuses on the immediate essentials: what the offer contains, what remains unclear, what the reader needs, and how to make a respectful counter. It is the best choice for a straightforward offer, a first-time negotiator, or anyone who needs to act without building a large compensation-research system. Its primary advantage is clarity. Its limitation is that the quality of the target still depends on the evidence the reader has gathered.
The intermediate prompt is for readers who have compensation sources but need a disciplined method for using them. It treats salary research as an evidence problem: sources are matched, weighted, deduplicated, challenged, and converted into a defensible range. This is the right choice when the reader expects to explain the basis for a request or when available data is plentiful but inconsistent. The advanced prompt adds operational control. It combines the offer decode and evidence model with concessions, competing timelines, scenario branches, red-team review, and live rehearsal.
All three prompts preserve the same division of labor. The reader supplies the offer, the evidence, the priorities, the honest deadlines, and the walk-away point. The AI supplies structure, comparison, questions, critique, and rehearsal. A reader can also move through the tiers sequentially: begin with the one-page decode, strengthen the market case with the evidence ledger, and adopt the complete playbook only when the negotiation’s complexity justifies it.
TAGS:
