AI prompts for managers and executives

Attack this strategy. Your job is to find where it breaks, not to improve it.

THE STRATEGY: [WHAT WE PLAN TO DO]
THE REASONING: [WHY WE THINK IT WILL WORK]
WHAT WE ARE BETTING ON: [KEY ASSUMPTIONS]
OUR SITUATION: [SIZE, RESOURCES, MARKET POSITION, CONSTRAINTS]
TIMEFRAME: [HOW LONG BEFORE WE EXPECT RESULTS]

Produce:

1. THE LOAD-BEARING ASSUMPTION - of everything I have said, the one that, if false, collapses the whole plan. Name it, and give the cheapest way to test it.

2. THE STRONGEST COUNTER-ARGUMENT - written as an intelligent critic would make it. Full strength, no strawman.

3. WHO ELSE HAS TRIED THIS - the general pattern, how it usually goes, and what distinguishes the cases that worked. Be honest about the base rate.

4. WHAT HAS TO BE TRUE - list the conditions required for this to work, and mark each: already true / probably true / unverified / unlikely.

5. THE COMPETITIVE RESPONSE - if this works, what do competitors do, and does our advantage survive it?

6. WHAT WE ARE NOT DOING - the opportunity cost of committing these resources here.

7. THE HONEST VERDICT - one paragraph. If the plan is weak, say so directly. If it is sound, say what makes it sound rather than agreeing.

Do not offer encouragement. Do not end on an upbeat note.

Help me decide between these options.

THE DECISION: [WHAT I AM CHOOSING BETWEEN]
OPTIONS: [LIST THEM]
WHAT I AM TRYING TO ACHIEVE: [THE UNDERLYING GOAL]
CONSTRAINTS: [BUDGET, TIME, PEOPLE, ANYTHING FIXED]
MY CURRENT LEAN: [WHICH ONE, AND WHY]
REVERSIBILITY: [how hard is this to undo]

Produce:

1. THE REAL QUESTION - restate the decision. Often the stated choice is a proxy for a different question. If it is, say so.

2. CRITERIA - derive 5-7 criteria from my goal and constraints, not generic ones. Weight each 1-5 by importance and justify each weight in a few words.

3. SCORING MATRIX - each option against each criterion, 1-5, with a one-line reason per cell. Weighted total at the bottom.

4. WHY THE WINNER MIGHT BE WRONG - the scoring's blind spots. What does this framework not capture?

5. MY LEAN, EXAMINED - I said I lean toward one. Is that supported by the analysis? If not, say so plainly and identify what I might be over-weighting.

6. REVERSIBILITY CHECK - if this is easily reversed, say that the right move may be to pick the fastest option and learn, not the best-scoring one.

7. WHAT WOULD CHANGE THE ANSWER - the one piece of information that would most alter the ranking, and how to get it.

Do not simply endorse my lean. If the analysis contradicts it, lead with that.

Help me decide whether to continue or stop this.

WHAT IT IS: [THE PROJECT/PRODUCT/INITIATIVE]
ORIGINAL GOAL AND SUCCESS CRITERIA: [WHAT WE SAID AT THE START]
HOW LONG IT HAS RUN: [TIME]
WHAT HAS BEEN SPENT: [MONEY, PEOPLE, TIME]
RESULTS SO FAR: [HONEST NUMBERS AND OUTCOMES]
WHAT WOULD BE NEEDED TO CONTINUE: [FURTHER INVESTMENT]
WHO IS ATTACHED TO IT: [INTERNAL POLITICS, HONESTLY]

Produce:

1. THE FRESH-START TEST - if this did not exist and someone proposed it today, with everything we now know, would we start it? Answer directly. This is the central question and everything spent so far is irrelevant to it.

2. AGAINST THE ORIGINAL CRITERIA - a table: Criterion | Target | Actual | Met? Be literal.

3. THE CASE FOR CONTINUING - at full strength. Include the legitimate reasons: learning curve, delayed effects, a known fixable problem.

4. THE CASE FOR STOPPING - at full strength. Include the opportunity cost of the resources.

5. SUNK COST CHECK - identify every argument in section 3 that is really 'we have already spent a lot'. Name them and set them aside.

6. THE MIDDLE OPTIONS - between continuing as-is and killing it: reduce scope, hand to one person, pause and revisit at a stated date, open-source it, sell it, change the goal. Each with what it costs and preserves.

7. THE DECIDING QUESTION - the single piece of evidence that should determine this, and whether we have it.

8. IF WE STOP - how to do it well: what to salvage, what to tell people, how to treat those attached to it.

Answer section 1 before anything else, and do not hedge it.

Write a board one-pager.

ORGANISATION: [WHAT IT DOES]
PERIOD: [QUARTER]
HEADLINE NUMBERS: [METRICS WITH PRIOR-PERIOD COMPARISON]
WHAT WENT WELL: [NOTES]
WHAT WENT BADLY: [NOTES - be honest, this is the section that matters]
DECISIONS OR APPROVALS NEEDED: [LIST]
BOARD'S KNOWN CONCERNS FROM LAST TIME: [LIST]

One page, roughly 500 words, structured:

1. THE QUARTER IN ONE SENTENCE
2. NUMBERS - table with prior period and variance. Flag anything off-plan.
3. WHAT CHANGED - three items, each two sentences
4. WHAT WENT WRONG - two items, each with: what happened, impact, what we are doing, and by when. Do not soften.
5. LAST MEETING'S CONCERNS - address each one explicitly, even the ones with no progress. Especially those.
6. ASKS - numbered, each with the decision, the options, the recommendation, and what happens if deferred

Rules:
- No adjectives on performance. 'Revenue grew 12%' not 'revenue grew strongly'.
- Section 4 must not be shorter than section 3.
- If a board concern from last time has had no progress, say 'no progress' and why, rather than reframing it.
- Anything you cannot evidence from my notes: mark [NEEDS DATA] rather than asserting it.

Prepare talking points for a team update.

AUDIENCE: [WHOLE COMPANY / TEAM / BOARD]
LENGTH: [MINUTES]
WHAT HAPPENED (results, news, changes): [PASTE]
THE ONE MESSAGE PEOPLE MUST REMEMBER: [MESSAGE]
SENSITIVE TOPICS: [e.g. layoffs rumours, missed targets]

Produce:
1. OPENING - 2-3 sentences that say the most important thing first
2. 3-5 TALKING POINTS - each with the point, one supporting fact, and what it means for the audience
3. THE HARD PART - how to address bad news or rumours honestly and specifically
4. LIKELY QUESTIONS - 6 questions people will ask, with honest answers; mark any where the answer is "we don't know yet" and suggest how to say that well
5. CLOSE - what happens next and when they will hear more

Rules: plain language, no corporate filler ("synergies", "right-sizing"). Do not promise anything I did not state.

Help me prepare for a difficult conversation with someone who reports to me.

THE ISSUE: [WHAT IS HAPPENING]
SPECIFIC INCIDENTS: [DATES AND WHAT HAPPENED - as factual as you can]
IMPACT: [ON THE TEAM, THE WORK, OR THEM]
WHAT I HAVE ALREADY TRIED: [PREVIOUS CONVERSATIONS OR SUPPORT]
OUTCOME I WANT: [WHAT CHANGES]
MY RELATIONSHIP WITH THEM: [CONTEXT]

Produce:

1. OPENING - exactly what to say in the first 30 seconds. Name the topic directly. No warm-up.
2. THE FACTS - my incidents restated as observable behaviour with impact, stripped of interpretation. Flag anything I have written as a judgement rather than an observation.
3. WHAT I MIGHT BE MISSING - three plausible explanations for this behaviour that I have not considered, including ones where the cause is me or the system.
4. QUESTIONS TO ASK - four, designed to let them explain rather than defend. Open, not leading.
5. WHAT GOOD LOOKS LIKE - the specific change, stated so both of us would know it when we see it.
6. IF IT GOES BADLY - responses for: they get upset, they disagree with the facts, they blame someone else, they say nothing.
7. WHAT I SHOULD NOT SAY - phrases to avoid in this specific conversation.

Do not write a script for the whole conversation. Prepare me, do not perform it for me.

Turn this strategy into quarterly objectives.

STRATEGY / ANNUAL GOAL: [STATEMENT]
WHY IT MATTERS: [THE REASONING]
TIMEFRAME: [WHICH QUARTER]
TEAMS INVOLVED: [LIST AND ROUGH SIZE]
CONSTRAINTS: [WHAT CANNOT CHANGE]
WHAT IS ALREADY COMMITTED: [EXISTING WORK THAT MUST CONTINUE]

Produce:

1. THE QUARTER'S ONE THING - if only one objective could be achieved, which, and why that one.

2. OBJECTIVES - maximum three. Each: a qualitative statement of what will be different by quarter end.

3. KEY RESULTS per objective - 2-3 each. Each must be:
   - A measurable outcome, not an activity. 'Ship feature X' is activity; 'X% of accounts using feature X weekly' is outcome.
   - Sourced from a metric that already exists, or accompanied by the work to start measuring it
   - Given a baseline (current value) and a target. Where I have not given a baseline, mark [BASELINE NEEDED].

4. TEAM CASCADE - for each team, what they own toward which key result, and what they should stop doing to make room.

5. CAPACITY CHECK - against my stated team sizes and existing commitments, is this plausible? If not, say so and name what must drop.

6. WHAT THIS QUARTER IS NOT ABOUT - explicitly, so teams can say no.

Rules:
- Never more than three objectives. If I gave you more, tell me which to cut and why.
- No key result may be a binary ship/not-ship.
- If a key result has no baseline and no way to measure it, it is not a key result.

Help me prepare for a difficult meeting. Play devil's advocate against my position.

MY POSITION: [WHAT I WANT TO HAPPEN]
WHY I WANT IT: [MY REASONING]
WHO I AM MEETING: [ROLE AND WHAT THEY CARE ABOUT]
THEIR LIKELY POSITION: [WHAT I THINK THEY WANT]
CONSTRAINTS I CANNOT CHANGE: [BUDGET, TIMELINE, POLICY ETC]

Produce:

1. THE STRONGEST CASE AGAINST ME - written as they would argue it, at full strength. Do not soften it.
2. MY THREE WEAKEST POINTS - where my reasoning is thin, and what evidence would fix each
3. LIKELY OBJECTIONS - a table: Objection | Why they will raise it | My response in two sentences | What I should NOT say
4. THE ZONE OF AGREEMENT - what we probably both want, stated in their language not mine
5. MY FALLBACK LADDER - four positions from ideal to walk-away, with the trigger for moving down each rung
6. ONE QUESTION to open with that would make them explain their real constraint

Do not reassure me. If my position is weak, say so in point 2.

Build an issue tree for this problem.

CLIENT AND CONTEXT: [DESCRIBE]
THE QUESTION: [e.g. "Why have profits fallen 20% this year?" or "Should we enter market X?"]
WHAT WE ALREADY KNOW: [FACTS]
DATA AVAILABLE: [DATA]
TIME AND BUDGET FOR THE WORK: [CONSTRAINTS]

Produce:
1. THE KEY QUESTION rewritten to be specific and answerable (who, what, by when)
2. THE ISSUE TREE - 3-4 levels, with branches that are mutually exclusive and together cover the whole problem (MECE). Show it as an indented list.
3. HYPOTHESES - for the most likely branches, a testable hypothesis each
4. ANALYSIS PLAN - for each hypothesis: the data or analysis that would prove or disprove it, and the source
5. PRIORITY - which 3 branches to investigate first and why (likely impact x ease of testing)
6. GAPS - any branch where overlap or missing areas mean the tree is not MECE yet

Do not jump to answers. The point is the structure.

The model agrees with whatever I say. Help me get an honest assessment.

WHAT I AM ASKING ABOUT: [YOUR PLAN, WORK, IDEA OR CLAIM]
MY PROMPT:
"""
[PASTE]
"""
WHAT I SUSPECT IS HAPPENING: [YOUR SENSE OF IT]
WHAT I ACTUALLY WANT TO KNOW: [THE REAL QUESTION]

Produce:

1. WHY THIS HAPPENS - models are trained to be helpful and agreeable, and they take the premise of a question as given. If I ask 'is my plan good?', the framing already suggests the answer I want. Agreement is the path of least resistance, and it takes deliberate instruction to get past it.

2. THE LEADING FRAMING IN MY PROMPT - quote where I have signalled the answer I want. Common tells: stating my position before asking, asking whether something is good rather than what is wrong with it, and describing my reasoning approvingly.

3. THE NEUTRAL REFRAMING - the same question asked without signalling. Frequently this alone changes the answer substantially.

4. THE ADVERSARIAL INSTRUCTION - asking for what is wrong rather than for an assessment. 'Identify the three weakest points and why a critic would attack them' produces more than 'what do you think'. Write it for my case.

5. THE WITHHOLD-MY-POSITION APPROACH - presenting the situation without saying what I think or what I have decided, so there is nothing to agree with. Often the most effective single change.

6. THE STEELMAN REQUEST - asking for the strongest case against, written as its best advocate would put it. This is more productive than asking for criticism, which produces hedged concerns.

7. THE 'DO NOT REASSURE ME' INSTRUCTION - explicit, and it works. Also: instructing it not to end on an encouraging note, because models reliably undo a critique in the final paragraph unless told not to.

8. THE FALSIFICATION QUESTION - asking what evidence would show I am wrong, and whether it exists. This converts an opinion request into an analytical one.

9. THE SEPARATE-EVALUATION APPROACH - presenting the work without saying it is mine. Models are less accommodating about work presented neutrally.

10. THE REWRITTEN PROMPT.

11. THE HONEST LIMIT - these techniques reduce accommodation and do not eliminate it. A model has no independent stake in my being right or wrong, which is useful, but it also has no real judgement about my situation. For a decision that matters, a person who knows the domain is not replaceable by a better-worded prompt.

Help me write an AI use policy.

THE ORGANISATION: [SIZE, SECTOR, WHAT IT DOES]
WHO IT APPLIES TO: [everyone / specific teams]
WHAT PEOPLE ARE ALREADY DOING: [CURRENT USE, INCLUDING UNOFFICIAL]
WHAT WE ARE WORRIED ABOUT: [YOUR CONCERNS]
WHAT TOOLS ARE APPROVED: [IF ANY]
REGULATORY CONTEXT: [ANY SECTOR REQUIREMENTS]

Produce:

1. THE REALISTIC STARTING POINT - people are already using these tools, including where there is no policy. A policy that prohibits everything drives use underground, where there is no oversight at all and no way to know what data has gone where. Design for the actual situation.

2. THE STRUCTURE - a usable policy covers:
   - What tools are approved, and how to request one
   - What data may and may not be entered, which is the most important section
   - Where output may be used and where it may not
   - What must be disclosed and to whom
   - Who is accountable for output
   - What to do when unsure

3. THE DATA SECTION - the highest-risk area and the one to write most carefully. What may never be entered: credentials, customer personal data unless the tool is approved for it, confidential information covered by contracts, and anything regulated in my sector. Be specific rather than general, because a general rule is interpreted variously.

4. THE APPROVED TOOLS - why the distinction matters: consumer and enterprise tiers differ on data retention, training use and processing location. Say what to check before approving a tool and what the approval should record.

5. THE OUTPUT ACCOUNTABILITY PRINCIPLE - the central rule. The person who uses AI-assisted output is accountable for it as if they had produced it themselves. This is clearer than trying to enumerate every acceptable use and it is the rule that actually works.

6. THE VERIFICATION REQUIREMENT - what must be checked before output is used: facts, figures, citations, code, and anything a person will rely on. Say what level of checking different kinds of work require.

7. THE HIGH-CAUTION LIST - where AI-assisted output must not be the basis of a decision without qualified review: decisions about individuals, anything with legal or regulatory weight, safety-related material, and anything going to a customer as authoritative.

8. THE DISCLOSURE RULES - when to say AI was involved: to customers, in submitted work, in creative or editorial contexts, and internally. Different contexts have different expectations and the policy should say which.

9. WHAT NOT TO INCLUDE - rules that cannot be enforced, technology-specific detail that dates immediately, and a prohibition on tools people will use anyway.

10. THE PRACTICAL SUPPORT - a policy alone changes little. What helps: an approved tool that is actually good enough, examples of acceptable and unacceptable use, and a named person to ask.

11. THE REVIEW - this area changes quickly. Set a review interval and name an owner.

12. THE ONE-PAGE VERSION - what people will actually read.

Requirements vary by sector and jurisdiction. Anything with regulatory implications needs legal and compliance input.

Write a decision memo.

THE DECISION AT STAKE: [WHAT NEEDS DECIDING]
MY RECOMMENDATION: [WHAT YOU THINK SHOULD HAPPEN]
WHO READS THIS: [ROLES, AND WHAT EACH CARES ABOUT]
CURRENT DIRECTION: [WHAT WILL HAPPEN IF NOBODY INTERVENES]
MY EVIDENCE: [DATA, EXPERIENCE, ANALYSIS]
THE COUNTER-ARGUMENT: [WHAT THE OTHER SIDE SAYS]
CONSTRAINTS: [BUDGET, TIME, POLITICS]

Structure:
1. RECOMMENDATION - first sentence. What you think should happen and the decision required.
2. WHY IT MATTERS NOW - the cost of the current direction, or the closing window.
3. THE ARGUMENT - three points maximum, each: claim, evidence, and what it means. Ordered by strength, strongest first, not by chronology.
4. THE STRONGEST OBJECTION - stated at full strength, as its best advocate would put it, then answered. Never a strawman; a reader who holds that view will stop reading the moment they see it misrepresented.
5. WHAT WOULD CHANGE MY MIND - the evidence that would make you wrong. This is the most persuasive paragraph in any memo, because it signals you are reasoning rather than advocating.
6. THE OPTIONS - including doing nothing, each with consequences. Your recommendation marked.
7. THE ASK - what you need, from whom, by when.

Rules:
- Under 1,000 words. Detail goes in an appendix.
- Every claim needs evidence or an explicit statement that it is judgement
- Acknowledge uncertainty where it exists. Overclaiming invites dismissal.
- No emotional appeals, no rhetorical questions
- Do not bury the recommendation to seem balanced

Then: THE READER MOST LIKELY TO DISAGREE, and whether this memo addresses their actual concern or a version of it you find easier to argue with.