AI prompts for finance professionals and financial analysts

Help me build a forecast.

WHAT I AM FORECASTING: [THE METRIC]
HISTORICAL DATA:
"""
[PASTE - PERIODS AND VALUES]
"""
HOW FAR FORWARD: [PERIODS]
WHAT THE FORECAST IS FOR: [THE DECISION]
WHAT I KNOW ABOUT WHAT DRIVES THIS: [CAUSAL FACTORS]
WHAT IS CHANGING: [ANYTHING PLANNED OR EXPECTED]

Produce:

1. WHAT THE HISTORY SHOWS - the trend, the variation around it, any seasonality, and any structural breaks where the pattern changed. Identify breaks explicitly; forecasting through a break using pre-break data is the most common forecasting error.

2. HOW MUCH HISTORY IS USABLE - if something changed partway through, only the post-change data is informative. Say how many periods you are actually forecasting from, which is often far fewer than the total.

3. THE BASELINE FORECAST - the simplest defensible method for this data: last value carried forward, average, trend extrapolation, or seasonal naive. Start here, because a simple baseline is frequently as accurate as anything elaborate and always easier to explain.

4. THE RANGE, NOT THE NUMBER - the forecast as low, likely and high, based on the historical variation. A single-number forecast is a false statement about the future. Say how wide the range should be given how variable the history is.

5. THE ASSUMPTIONS - each explicitly: that the trend continues, that seasonality repeats, that nothing changes structurally, and that the drivers I named continue to behave as they have. List them, because these are what the forecast actually rests on.

6. WHAT WOULD BREAK IT - the specific events that would make this forecast wrong, and roughly how wrong.

7. THE PLANNED CHANGES - I told you what is changing. The historical data cannot inform their effect. Handle them as an explicit adjustment with its own stated assumption, separate from the statistical forecast, rather than folding them in invisibly.

8. THE HORIZON WARNING - forecast accuracy degrades with distance. Say at what horizon this forecast stops being informative, given the variability in my data.

9. HOW TO USE IT - given my decision: does the decision change across the range? If it is the same at the low and high case, stop forecasting and decide.

10. HOW TO CHECK IT - record the forecast now and compare later. Forecasts that are never scored never improve.

Do not produce a precise-looking number. Produce a range and its assumptions.

Help me build scenarios.

THE SITUATION: [WHAT YOU ARE PLANNING FOR]
THE DECISION: [WHAT YOU NEED TO DECIDE]
TIME HORIZON: [HOW FAR OUT]
WHAT IS UNCERTAIN: [THE KEY UNKNOWNS]
WHAT YOU KNOW: [THE FIXED FACTS]
WHAT YOU CAN CONTROL: [YOUR LEVERS]

Produce:

1. THE CRITICAL UNCERTAINTIES - of everything uncertain, the two that most affect the outcome and are least predictable. Rank all my stated unknowns by (impact x unpredictability) and pick the top two. Things that are uncertain but low-impact do not need scenarios.

2. THE SCENARIO SET - built from combinations of those two uncertainties. Three or four scenarios, each with a short memorable name. For each:
   - What is true in this world, described concretely
   - How you would recognise it early
   - What it means for my decision
   - What would be the right move in this scenario alone

   Scenarios must be genuinely different, plausible, and internally consistent. Avoid the common failure of good case, bad case and middle case - that is a range, not a set of scenarios, and it produces no insight.

3. THE ROBUST CHOICES - what is the right thing to do across all scenarios. This is the most valuable output: decisions that work regardless of which future arrives.

4. THE SCENARIO-DEPENDENT CHOICES - what you should not commit to yet because the right answer differs by scenario. And what would let you defer them cheaply.

5. THE SIGNPOSTS - early indicators that would tell you which scenario is developing, and roughly when you would see each. This is what turns scenarios from an exercise into a monitoring system.

6. THE OPTIONS TO PRESERVE - cheap things to do now that keep possibilities open: a small pilot, a shorter contract, a reversible commitment. Optionality is worth paying for when uncertainty is high.

7. THE UNACCEPTABLE OUTCOME - the scenario you could not survive, however unlikely. What would protect against it, and what that protection costs.

8. WHAT I AM ASSUMING IS FIXED that might not be. The things I listed as known are themselves assumptions; challenge the shakiest.

Do not produce a forecast. The point is to prepare for several futures, not to pick one.

Review this forecast.

THE FORECAST:
"""
[PASTE - THE NUMBERS, THE PERIODS, AND ANY STATED METHOD]
"""

WHAT IT IS FORECASTING: [THE METRIC]
WHO PRODUCED IT: [AND THEIR INTEREST IN THE ANSWER]
WHAT DECISION DEPENDS ON IT: [THE STAKES]
HISTORICAL DATA IF AVAILABLE: [PASTE]

Produce:

1. THE ASSUMPTIONS - stated and unstated. Every forecast rests on assumptions; a forecast that does not state them is not reviewable. List what must be true for these numbers to hold, and mark which were stated and which you had to infer.

2. THE GROWTH CHECK - what growth rate does this imply, period on period? Compare it to the historical rate if I gave you one, and to what is plausible for this kind of thing. Forecasts that imply sustained growth far above anything historically achieved need justification that is usually absent.

3. THE HOCKEY STICK TEST - does the forecast show flat or declining recent history followed by sharp improvement? If so, what specifically causes the inflection? An unexplained inflection is the single most common sign of a forecast built backwards from a desired conclusion.

4. THE CONSTRAINT CHECK - does the forecast respect real limits? Market size, capacity, headcount required, physical or regulatory constraints. Compute what the forecast implies in units other than the headline figure: customers needed, units per day, staff required. Implied figures are where over-optimism becomes visible.

5. THE MISSING COSTS - if it is a financial forecast, what scales with growth that is not shown: support, infrastructure, hiring, churn at higher volumes.

6. THE UNCERTAINTY - is there any? A single-line forecast with no range is a statement of intent, not a projection. If no range is given, ask for one.

7. THE INCENTIVE CHECK - I told you who made it. Do they benefit from an optimistic number? This does not make it wrong, but it determines how much independent verification you should want.

8. THE BASE RATE - how do forecasts of this type usually perform? Say honestly that most such forecasts overstate, and by roughly how much, if that is the pattern.

9. THE QUESTIONS TO ASK - specific and answerable, phrased neutrally. The most useful is usually: what would have to be true for this, and what happens if it is not?

10. THE VERDICT - credible / optimistic but defensible / not supported by the stated basis.

Help me model the financial effect of this decision.

THE DECISION: [WHAT YOU ARE CONSIDERING]
WHAT IT COSTS: [UPFRONT AND ONGOING]
WHAT IT SHOULD RETURN: [THE BENEFIT YOU EXPECT]
CURRENT SITUATION: [THE BASELINE - what happens if you do nothing]
TIME HORIZON: [PERIOD]
WHAT YOU KNOW AND WHAT YOU ARE GUESSING: [BE EXPLICIT]

Produce:

1. THE BASELINE - what happens if you do nothing. Every comparison is against this, and it is frequently omitted, which makes the proposed option look better than it is. Model the do-nothing case first.

2. THE COST MODEL - all of it, over the horizon:
   - Upfront and ongoing
   - Staff time, costed
   - The things people forget: training, migration, integration, support, maintenance, the cost of running both old and new during transition, and the cost of stopping if it does not work
   - Opportunity cost: what does not happen because resources went here

3. THE BENEFIT MODEL - with the mechanism stated. Not 'improves efficiency' but the specific chain: this changes, which means that, which is worth this much. Where a link in the chain is an assumption, mark it.

4. THE TIMING - when costs fall and when benefits arrive. Benefits almost always arrive later and more slowly than expected. Model a realistic ramp rather than full benefit from day one.

5. THE NET PICTURE - period by period, cumulative, and the point at which it turns positive if it does.

6. THE SENSITIVITY - the two or three assumptions that most affect the result. Show the outcome at pessimistic, expected and optimistic values for each. This matters more than the central estimate.

7. THE BREAK-EVEN - what would each key assumption need to be for this to merely break even? Stating it this way is often more informative than the projection: 'this needs a 12% improvement to break even, and we currently see 4%'.

8. WHAT IS NOT IN THE MODEL - effects that are real but not quantified: risk reduction, morale, flexibility, strategic position. Name them so they are considered rather than ignored, and do not invent numbers for them.

9. THE HONEST SUMMARY - does this stack up? If it only works under optimistic assumptions on every variable simultaneously, say so.

I am not asking for financial advice, only for this arithmetic laid out with its assumptions visible.

Help me build a 13-week cash flow forecast.

BUSINESS: [DESCRIBE]
OPENING CASH BALANCE: [AMOUNT]
REGULAR RECEIPTS: [CUSTOMERS, AMOUNTS, TIMING, PAYMENT TERMS]
REGULAR PAYMENTS: [PAYROLL, RENT, SUPPLIERS, LOANS, TAXES - AMOUNTS AND DATES]
ONE-OFF ITEMS: [LIST]
TOOL: [Excel / Google Sheets]

Produce:
1. THE LAYOUT - rows (receipts by type, payments by type, net flow, opening and closing balance) and 13 weekly columns
2. FORMULAS for my tool, with cell references explained
3. ASSUMPTIONS TAB - every assumption listed with where it is used
4. A WARNING LINE - conditional formatting when closing cash falls below [MINIMUM BALANCE]
5. HOW TO UPDATE IT WEEKLY - replace forecast with actuals and roll forward
6. The 3 levers if a shortfall appears (accelerate receipts, delay payments, short-term funding) with what to check for each

Rules: do not invent amounts; use [AMOUNT] placeholders for anything I did not give.

Analyse period-over-period variance.

CURRENT PERIOD DATA:
"""
[PASTE]
"""
PRIOR PERIOD DATA:
"""
[PASTE]
"""
WHAT CHANGED IN THE BUSINESS BETWEEN THEM: [PRICE CHANGES, CAMPAIGNS, SEASONALITY, STAFFING, OUTAGES, ANYTHING]

Produce:

1. VARIANCE TABLE - Metric | Prior | Current | Absolute change | % change | Material? (yes/no)
   Define material as more than 10% or more than [THRESHOLD] absolute, whichever you judge more meaningful, and state which rule you used.

2. FOR EACH MATERIAL VARIANCE:
   - Candidate explanations, ranked by plausibility
   - Which of my stated business changes could account for it
   - What data would confirm or rule out each explanation
   - Confidence: high / medium / low

3. VARIANCES THAT CANCEL OUT - places where two movements offset and the headline number hides real change underneath.

4. WHAT I CANNOT EXPLAIN - list these plainly. Do not force an explanation onto every number.

Rules:
- Correlation with a business change is not causation. Say 'consistent with' not 'caused by'.
- Where the change is within the normal range of past variation, say so and do not explain it.
- Never attribute a movement to seasonality unless I gave you prior-year data.

Write an executive summary from this data.

DATA:
"""
[PASTE CSV OR TABLE]
"""

WHAT THE DATA IS: [DESCRIPTION]
PERIOD: [DATES]
AUDIENCE: [ROLE AND WHAT THEY CARE ABOUT]
THE DECISION THIS INFORMS: [WHAT THEY WILL DO WITH IT]

Produce:

**Bottom line** (40 words): what the data says, and what to do about it.

**Three findings**: each one sentence of claim, then one sentence of supporting number. Ordered by how much they should change the reader's mind, not by how interesting they are.

**What this does not tell us**: the limitations. Sample size, missing segments, confounders, anything measured as a proxy. Be specific to this dataset.

**Recommendation**: one action, with the expected effect and how you would know if it worked.

Rules:
- Every number you cite must appear in the data. Do not compute a statistic you cannot show.
- If a trend is within normal variation, say so rather than narrating it as a change.
- Do not use 'significant' unless you mean statistically, and then show the basis.
- If the data does not support a confident conclusion, the bottom line should say that.

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.

Help me build a spreadsheet model.

WHAT IT MODELS: [THE SITUATION]
WHAT I WANT TO WORK OUT: [THE OUTPUT]
INPUTS I HAVE: [KNOWN VALUES]
ASSUMPTIONS I NEED TO MAKE: [WHAT IS UNCERTAIN]
TIME PERIOD: [IF IT PROJECTS FORWARD]
WHO ELSE WILL USE IT: [AUDIENCE]

Produce:

1. THE STRUCTURE - three separate areas, and explain why this separation matters:
   - INPUTS sheet: every number someone might change, each in its own labelled cell, colour-coded as an input
   - CALCULATIONS sheet: the workings, one step per row, each row labelled
   - OUTPUT sheet: the results and any charts
   No hardcoded number may appear inside a formula. Every one lives in the inputs area. This is the single rule that makes a model auditable.

2. THE INPUT LIST - a table: Input | Value | Unit | Source or basis | Confidence (known / estimated / guessed)

3. THE CALCULATION CHAIN - each step: what it computes, the formula, and the row it depends on. Someone should be able to trace any output back to inputs by reading down.

4. THE FORMULAS - written out, with cell references based on the layout you propose.

5. SENSITIVITY - the three inputs that most affect the output. Build a simple table showing the output at low, base and high values for each. This is usually more informative than the model's headline answer.

6. THE CHECKS - built-in validation: totals that must reconcile, values that cannot be negative, percentages that must sum to 100. Put these in a visible checks row that shows OK or ERROR.

7. WHAT THE MODEL CANNOT TELL YOU - its structural limitations. A model projects the logic you built; it does not predict reality.

8. DOCUMENTATION - a notes area stating what this models, who built it, when, and every assumption. Models outlive the memory of the person who built them.

Rules:
- No hardcoded numbers inside formulas, ever
- No circular references
- One calculation per cell; do not nest six operations into one formula
- Label every row

Help me sanity-check this number.

THE CLAIM: [THE NUMBER AND WHAT IT SUPPOSEDLY SHOWS]
WHERE IT CAME FROM: [SOURCE]
HOW IT WAS CALCULATED: [IF STATED]
SUPPORTING DATA: [PASTE, if you have any]
CONTEXT: [WHAT DECISION DEPENDS ON THIS]

Produce:

1. THE DEFINITION CHECK - what exactly is being counted, over what period, for which population? Most wrong numbers are not calculation errors; they are definition mismatches. Name every ambiguity in how this is stated.

2. THE ORDER OF MAGNITUDE CHECK - is this number plausible at all? Work out roughly what it should be from independent knowledge and compare. A back-of-envelope estimate catches errors that detailed checking misses.

3. THE ARITHMETIC - if I gave you the calculation, redo it. If I gave supporting data, compute it yourself and compare.

4. THE COMMON ERRORS to check for in a number of this type:
   - Percentage of what? A different denominator changes everything.
   - Percentage change versus percentage point change - frequently confused, and the difference is large
   - Double counting, especially where records can appear twice
   - A rate quoted without its base, so 300% growth turns out to be from two to eight
   - Averages hiding a skewed distribution; the median may tell a different story
   - A period comparison where the periods are not equal length or are seasonally different
   - Currency, units or scale mismatches (thousands versus millions)
   - Survivorship: measuring only the ones that remained

5. WHAT WOULD MAKE THIS NUMBER TRUE, and what would make it false. Both.

6. THE QUESTIONS TO ASK the person who produced it, phrased precisely and without accusation. Usually: what exactly is in the numerator and denominator, what period, and what was excluded.

7. THE VERDICT - plausible / needs verification / likely wrong, with reasoning.

8. HOW MUCH IT MATTERS - given the decision, does the uncertainty change what you should do? Sometimes the number is unverifiable and the decision is the same either way.

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.

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.