AI prompts for consultants

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.

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.

Analyse this competitor.

COMPETITOR: [NAME AND WHAT THEY DO]
WHAT I KNOW ABOUT THEM: [PASTE - THEIR SITE COPY, PRICING, REVIEWS, JOB ADS, ANYTHING]
OUR POSITION: [WHAT WE DO AND HOW WE DIFFER]
WHERE WE COMPETE: [SEGMENT, GEOGRAPHY, CHANNEL]

Produce:

1. THEIR STRATEGY AS THEY WOULD STATE IT - one paragraph, written from inside their business, taking them seriously.

2. WHO THEY ARE ACTUALLY FOR - the customer they serve best, inferred from pricing, positioning and features. Often narrower than their marketing claims.

3. EVIDENCE TABLE - Claim about them | Evidence | Source | Confidence (observed / inferred / assumed)
   Mark clearly what you know versus what you are guessing.

4. WHAT THEIR JOB ADS AND PRICING REVEAL - hiring and price changes are the two most honest public signals of strategy. What do they suggest?

5. WHERE THEY ARE STRONG - and specifically, where they would beat us head to head.

6. WHERE THEY ARE STRUCTURALLY WEAK - not 'their UI is dated' but constraints they cannot easily escape: their cost base, their existing customers' expectations, their channel, their funding model.

7. THE CUSTOMER THEY CANNOT SERVE WELL - and whether that is a market worth having.

8. WHAT I SHOULD NOT COPY - things they do that work for them because of their situation and would not work for mine.

Do not assert anything you cannot trace to my input. Mark inference as inference.

Run a SWOT analysis that leads somewhere.

BUSINESS/UNIT: [WHAT IT IS AND DOES]
MARKET: [WHO YOU SELL TO AND WHO ELSE DOES]
CURRENT SITUATION: [HONEST DESCRIPTION - SIZE, TRAJECTORY, RESOURCES]
THE DECISION THIS SUPPORTS: [WHAT YOU ARE TRYING TO DECIDE]

Rules for each quadrant:
- STRENGTHS: only things that are (a) true, (b) relevant to customers, and (c) hard for a competitor to copy within a year. Anything that fails all three is not a strength. Say which test each one passes.
- WEAKNESSES: only things that cost you customers or money. Include at least one uncomfortable one.
- OPPORTUNITIES: only external changes you could actually act on with current resources. 'Growing market' is not an opportunity, it is a condition.
- THREATS: ranked by likelihood x impact, with the earliest signal you would see for each.

No entry may be a single adjective. Each must be a sentence with evidence or an example.

Then - and this is the actual output - produce the cross-analysis:
- S+O: which strength lets you capture which opportunity. The best move on the board.
- W+T: which weakness makes which threat dangerous. The thing to fix first.
- S+T: which strength defends against which threat.
- W+O: which weakness will stop you taking which opportunity.

End with the single highest-leverage action from the cross-analysis, and what you would stop doing to fund it.

Help me size this opportunity.

WHAT I WANT TO SELL: [PRODUCT AND PRICE]
WHO WOULD BUY IT: [CUSTOMER DESCRIPTION]
WHERE: [GEOGRAPHY]
WHAT I KNOW: [ANY DATA YOU HAVE - market reports, your own numbers, competitor information]
WHY I AM SIZING IT: [investment decision / prioritisation / pitch]

Produce:

1. THE HONEST FRAMING - market sizing is an estimate with wide error bars, not a measurement. Say so upfront, and state that the purpose is to determine an order of magnitude, not a number.

2. BOTTOM-UP ESTIMATE - build from units: how many potential customers exist, what proportion have the problem, what proportion would pay, at what price, how often. Show every assumption on its own line with its source or the fact that it is a guess.
   This is the only estimate worth much. Do it first.

3. TOP-DOWN CHECK - if a published market figure exists, what share would you need to hit the bottom-up number? If the answer is an implausible share, the bottom-up estimate is wrong. Use top-down only as a sanity check, never as the estimate; published market figures are usually defined too broadly to mean anything for a specific product.

4. THE ASSUMPTION AUDIT - every assumption, with: the value, the basis, and the effect on the total if it is off by half or double. Rank by sensitivity. Usually two assumptions drive the whole answer.

5. THE SERVICEABLE PORTION - of the total, what can you actually reach given your channel, geography, language and sales capacity? This is far smaller than the total and is the number that matters for a decision.

6. THE REALISTIC SHARE - what share of the serviceable market is plausible in three years, given the competition. Be conservative and say what comparable businesses achieve.

7. THE RANGE - present the answer as a range with a low, likely and high case, never a single number.

8. WHAT WOULD MAKE THIS WRONG - the assumption most likely to be false, and the cheapest way to test it before committing.

9. THE DECISION CHECK - given why I said I am sizing this, does the answer actually change the decision? If the opportunity is clearly big enough or clearly too small under every case, stop analysing and decide.

Do not produce a confident number. Produce a range and its assumptions.

Convert this report into a slide narrative.

REPORT:
"""
[PASTE]
"""

AUDIENCE: [WHO]
TIME SLOT: [MINUTES]
THE ONE THING THEY MUST LEAVE BELIEVING: [YOUR ARGUMENT]

Produce a slide-by-slide outline. Budget roughly 2 minutes per slide.

For each slide:
- SLIDE TITLE: written as a full assertion, not a label. 'Churn is concentrated in month two' not 'Churn analysis'.
- WHAT IS ON IT: the chart, table or three bullets - be specific about which data
- WHAT YOU SAY: two sentences of speaker notes
- WHY IT IS HERE: which step of the argument this advances. If you cannot answer, cut the slide.

Structure the deck as an argument: situation, complication, question, answer, evidence, implication, ask. Do not mirror the report's section order.

Also output:
- CUT LIST: what from the report does not make the deck, and where it goes instead (appendix / pre-read / nowhere)
- THE THREE QUESTIONS the audience will ask, and which slide should answer each
- If the time slot cannot hold the argument, say so and give the shorter version.

Help me build a presentation.

WHAT I NEED TO PRESENT: [THE SUBJECT]
THE POINT: [WHAT THE AUDIENCE SHOULD CONCLUDE OR DECIDE]
AUDIENCE: [WHO, WHAT THEY KNOW, WHAT THEY CARE ABOUT]
TIME SLOT: [MINUTES, INCLUDING OR EXCLUDING QUESTIONS]
MY MATERIAL: [NOTES, DATA, RESEARCH]
CONTEXT: [meeting / conference / pitch / internal update / training]
WILL IT BE READ WITHOUT ME: [yes / no]

Produce:

1. THE ARGUMENT IN ONE SENTENCE - what this deck argues. If it is 'an overview of X', that is a document, not a presentation. Push me to a claim.

2. THE STRUCTURE - as an argument, not a topic list: the situation, the complication, the question it raises, your answer, the evidence, and the implication. Adapt to my context.

3. THE SLIDE PLAN - each slide: an assertion title stating the point, what is on the slide, what I say, and which step of the argument it advances. If a slide advances nothing, cut it.

4. ASSERTION TITLES - this is the single highest-value change to any deck. 'Q3 revenue' is a label; 'Revenue fell in Q3 because two large accounts churned' is a title. Someone reading only the titles should get the whole argument. Write every title this way.

5. THE SLIDE COUNT - for my time slot. Budget generously; every deck runs long. State the realistic number and cut the plan to fit.

6. WHAT GOES ON THE SLIDE VERSUS WHAT YOU SAY - a slide the audience reads is a slide they are not listening to. Slides carry what must be seen: a chart, a number, an image, a short assertion. Everything else is spoken.

7. THE READ-WITHOUT-ME PROBLEM - I said whether this will be circulated. If yes, the resolution is not to cram the slides with text; it is a separate document or full speaker notes. Say which and why.

8. THE ONE SLIDE THAT MATTERS - if they remember one, which. Make sure it is designed to be the memorable one.

9. THE QUESTIONS - the four the audience will ask, which slide answers each, and what to have in an appendix.

10. THE CUT LIST - ordered, for when time is shorter than planned.

Explain these financial statements to my client in plain language.

CLIENT: [WHO THEY ARE AND HOW FINANCIALLY CONFIDENT THEY ARE]
STATEMENTS (paste figures or a summary): [P&L / BALANCE SHEET / CASH FLOW]
PERIOD AND COMPARISON PERIOD: [PERIODS]
WHAT THEY ASKED OR WORRY ABOUT: [QUESTION]

Write:
1. THE HEADLINE - 3 sentences on how the business did, in everyday words
2. WHAT CHANGED AND WHY - the 3-5 biggest movements, each with the figure, the change, and the likely reason. If the reason is not in the data, write [ASK CLIENT: ...] rather than guessing.
3. CASH vs PROFIT - explain the difference using their own numbers if they differ
4. WATCH POINTS - up to 3 things to keep an eye on
5. QUESTIONS TO DISCUSS at our next meeting

Rules:
- Use only the numbers provided. Show any calculation you make.
- No jargon without a one-line explanation.
- Do not give tax, legal or investment advice - flag topics that need a proper professional review instead.

Analyse this data.

DATA:
"""
[PASTE]
"""

WHAT IT IS: [DESCRIPTION AND SOURCE]
MY QUESTION: [WHAT YOU WANT TO KNOW]
WHAT DECISION THIS INFORMS: [WHAT YOU WILL DO WITH IT]
WHAT I EXPECT TO FIND: [YOUR PRIOR - be honest]

Produce:

1. THE DESCRIPTIVE PICTURE first - counts, ranges, distributions, and time coverage. Do this before any comparison. Most questions are answered here.

2. THE ANSWER TO MY QUESTION - stated directly, with the numbers that support it and the calculation shown.

3. THE CONFIDENCE - how strongly the data supports this. Consider: sample size, whether the difference exceeds normal variation, whether the period is representative, and whether the comparison is like for like. Say plainly if the answer is 'this data cannot tell you'.

4. WHAT WOULD EXPLAIN THIS OTHER THAN MY HYPOTHESIS - alternative explanations for the pattern. At minimum consider: a change in what was measured or how, a composition change (the mix of things being averaged shifted), seasonality, an outlier driving the aggregate, and survivorship (you only see what remained).

5. THE COMPOSITION CHECK - run this specifically. An overall average can move while every subgroup stays flat, purely because the mix changed. This is Simpson's paradox and it is common enough to check every time.

6. THE OUTLIER CHECK - is the finding driven by a few extreme records? Show the result with and without them.

7. WHAT I EXPECTED VS WHAT IS THERE - I told you my prior. Where the data contradicts it, say so directly. Where the data is consistent with it, note that consistency is weaker evidence than it feels.

8. WHAT THIS DOES NOT SHOW - the limitations, specific to this dataset.

9. THE DECISION - given what I said I would do with this, does the analysis support that action? If the finding is real but too small to matter, say so.

Rules:
- Show the arithmetic for anything I might need to check
- Never say 'significant' without meaning it statistically and showing the basis
- Correlation is not causation; say 'associated with' and name what would establish causation

Help me research this topic systematically.

TOPIC: [WHAT YOU WANT TO UNDERSTAND]
WHY: [WHAT DECISION OR OUTPUT THIS FEEDS]
WHAT I ALREADY KNOW: [YOUR CURRENT UNDERSTANDING]
HOW DEEP: [a working understanding / enough to write about it / enough to make a large decision]
TIME AVAILABLE: [HOURS OR DAYS]

Produce:

1. THE QUESTION, SHARPENED - restate what I am actually trying to find out. Broad topics produce broad reading; a specific question produces an answer. If my topic is too broad for my stated time, narrow it and say so.

2. THE SUB-QUESTIONS - break it into the specific things you would need to know. Ordered, because some answers determine which others matter.

3. WHAT KIND OF ANSWER EXISTS - be honest about this before I start reading. Is this a settled factual matter, an area of genuine expert disagreement, a matter of definition, or something where good data does not exist? This determines whether I am looking for the answer or for the range of positions.

4. SOURCE TYPES IN ORDER - for this specific topic, where the good information is and in what order to approach it: primary sources and original data, academic or technical literature, industry or regulatory publications, practitioner accounts, and journalism. Note which source types are unreliable for this topic and why.

5. WHO WOULD KNOW - the kinds of people or organisations with direct knowledge, and what each would be able to tell me that documents cannot.

6. THE SEARCH STRATEGY - the specific terms to use, including the technical vocabulary I may not know. Name the jargon, because searching in the wrong vocabulary is the most common reason research stalls.

7. THE CONFLICT MAP - where I should expect to find disagreement, and what usually underlies it: different definitions, different data, different time periods, or different interests.

8. WHAT TO BE SCEPTICAL OF - the claims in this area that get repeated without evidence, and any figure widely cited that should be traced to its source.

9. WHEN TO STOP - the signal that further reading is not adding anything, so I do not research indefinitely.

10. THE NOTE STRUCTURE - how to record findings so they are usable later: claim, source, date, confidence, and what it contradicts.

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 set my freelance / consulting rates.

WHAT I DO: [SERVICE]
MY EXPERIENCE: [YEARS, SPECIALISM, RESULTS]
MARKET / CLIENTS: [WHO AND WHERE]
TARGET YEARLY INCOME BEFORE TAX: [AMOUNT AND CURRENCY]
BUSINESS COSTS PER YEAR: [SOFTWARE, EQUIPMENT, INSURANCE, ETC.]
REALISTIC BILLABLE HOURS PER WEEK: [HOURS]
WEEKS OFF PER YEAR: [WEEKS]
WHAT OTHERS CHARGE (if known): [RANGE]

Calculate, showing the arithmetic:
1. My minimum hourly rate to hit the target (target + costs / billable hours per year)
2. A day rate and a half-day rate
3. Three project price examples for typical jobs: [DESCRIBE 2-3 TYPICAL JOBS]

Then:
- Compare with the market range I gave and say whether I am under, within or over
- Suggest when to use hourly, day or fixed-price, and the risks of each
- Write 2 sentences I can use when a client asks "why this price?"
- Point out any assumption that looks unrealistic (e.g. 40 billable hours a week is rarely achievable)