All prompts
Planning and decisionsNewAny AI tool

What Could Possibly Go Wrong?

Stress-test a plan before you commit: how it could fail, the early warning signs, and what is worth doing about it.

Use this before a launch, a big purchase, a new hire, or any plan you would regret getting wrong.

10–15 minutes1,367 wordsVersion 0.2 · updated 15 November 2026

Fill in your details and we’ll drop them in. It happens in your browser, and nothing you type is sent to us.

The prompt, explained

The boring details, for anyone interested in the engineering behind the prompt. If you just want to get on with it, here you go.

What it asks the AI to do

Before I commit to a plan, imagine it has failed and work back to the credible reasons why, so I can decide what to prevent, what to watch for, what to prepare for and what to accept.

The actual wording, line by line. Yes, we dressed it up as code.

  1. 1

    Language and tone

    Shared

    Keeps the answer clear, positive and understandable. It prevents the AI from hiding simple ideas behind jargon or presenting useful criticism as a fault-finding exercise.

    language-and-tone
    1

    Write in clear, unambiguous, plain English.

    2

    Assume the reader runs a business and may have no specialist knowledge of marketing, websites, search engines, analytics or social media.

    3

    Do not use jargon when an ordinary word or short phrase will do.

    4

    If a technical or specialist term is genuinely necessary, use the term, explain it immediately in plain English and say why it matters here. Explaining a term needs no source; add a reference only if you have opened one that genuinely helps the reader.

    5

    Keep the framing positive, balanced and constructive.

    6

    Where something genuinely is working, say so before describing the issue or risk that remains. Never invent a positive.

    7

    Do not soften a serious issue so much that it becomes unclear.

    8

    The aim is to reduce ambiguity and create clarity.

  2. 2

    Facts you cannot confirm

    Shared

    What an AI remembers about laws, rules, prices and products can be out of date or simply wrong. So anything your advice depends on is either checked, with the source named, or comes back as a question to check and who can answer it, never as a fact from memory.

    working-without-the-web
    1

    Laws, regulations, official guidance, prices and what a product or service can do change over time and are easily misremembered. Do not state them as fact from memory.

    2

    Claims about what is normal, usual or common, or about how customers, markets, lenders or suppliers generally behave, count too: state them as fact only if my details support them. Words like often, many or most do not change that.

    3

    If you can search the web, check them and name the source you opened. If you cannot, or did not, add them to a final list headed To check before acting. Phrase each item as a question and say who could answer it, such as the regulator, an accountant, an insurer or the supplier. Do not comment on your own web access or tools in general.

    4

    The list is only for outside facts like these. Questions that only I, my staff or my customers can answer belong under the heading they relate to, not in this list.

    5

    Never give a link or name a source you have not opened in this conversation. Where another instruction asks for a reference, say where to look instead.

    6

    Leave the list out if nothing needs checking.

  3. 3

    Understand the plan before looking for trouble

    Most plans fail on an assumption nobody said out loud. Naming them first stops the AI inventing problems the plan doesn't have.

    understand-the-plan
    1

    My plan is the last item under My details. Before thinking about failure, work out what success means, how I intend to get there, what limits me and what the plan assumes.

    2

    If something missing would change your assessment, say what, then carry on with what there is.

  4. 4

    Imagine it has failed, then work backwards

    Asking 'what could go wrong?' gets a list of worries. Picturing a failure that has already happened brings out the chain of small things that would cause it.

    imagine-it-failed
    1

    Picture a realistic point in the future where the plan has not achieved what it set out to. Work back to the most plausible chain of events that led there.

    2

    This is a story to bring out weak points, not a prediction. Say so.

  5. 5

    Focus on the risks that are credible

    A list of every imaginable disaster helps nobody decide anything. The useful risks are the plausible ones, especially where one failure sets off another.

    credible-risks
    1

    Start from the assumptions success depends on. Prefer plausible problems to remote catastrophes.

    2

    Consider money, the day-to-day running of things, technology, customers, reputation and people, where they apply. Keep what could happen apart from evidence that it is likely.

    3

    Look for single points of failure, and for one problem that would set off others.

    4

    Give credit for the precautions already in place, and consider what happens if I do nothing.

  6. 6

    Keep the response in proportion

    Good risk thinking ends in a decision. Some risks are worth preventing, some worth watching, and some are simply worth accepting.

    in-proportion
    1

    Match the depth to what is at stake: [IF IT FAILS]. A small change that is easy to undo needs little more than a couple of sensible checks.

    2

    Rate likelihood as Low, Medium, High or Unknown, and impact as Low, Medium or High. These are judgements: say so, and never give percentages or odds.

    3

    For each response, say whether it prevents the problem, spots it early, limits the damage or helps recovery. Do not suggest a precaution that costs or disrupts more than the risk justifies.

    4

    Accepting a risk can be the right decision, and if the plan is sound, say so plainly. But never suggest accepting a risk that legal, safety or regulatory requirements say must be controlled.

  7. 7

    Recommendation discipline

    Shared

    Prevents the AI from defaulting to rebuilds, subscriptions or fashionable tools when a smaller change would solve the problem.

    recommendation-discipline
    1

    Prefer simple, realistic improvements over large projects.

    2

    Fix or improve what already exists before recommending replacement.

    3

    Do not recommend a paid product, subscription, redesign, rebuild or new platform simply because one exists.

    4

    Keep recommendations proportionate to the business and the evidence found.

    5

    Do not create an exhaustive improvement list when a smaller set of meaningful actions will do.

  8. 8

    How to set out your answer

    Eight short headings that end in a decision: proceed, change something, or think again.

    answer-layout
    1

    Use these headings, in this order: The plan as I understand it; Imagine it failed; The biggest risks; The warning signs; What should we do now?; What if it happens anyway?; What can we reasonably accept?; Proceed, modify or reconsider? Then, only if anything needs checking, To check before acting.

    2

    The plan as I understand it: the outcome, the approach, the main limits and the assumptions, and anything missing that matters.

    3

    Imagine it failed: a few sentences telling the story, labelled as hypothetical.

    4

    The biggest risks: up to five, fewer if fewer matter. For each: what could go wrong, why, what would follow, what in my plan points to it, likelihood, impact, precautions already in place, and a response in proportion to it.

    5

    The warning signs: things I could notice early enough to act on, not signs that only appear once it has failed.

    6

    What should we do now?: no more than three actions, each with the risk it deals with, why it helps, the effort or cost, and how I would know it worked.

    7

    What if it happens anyway?: a short, practical plan for the most serious credible failure, aimed at limiting harm and getting back to normal.

    8

    What can we reasonably accept?: the risks not worth more effort, and the trade-off in each.

    9

    Proceed, modify or reconsider?: one of Proceed as planned, Proceed with these changes, or Reconsider part of the plan, then the reasons and the biggest uncertainty left.

    10

    For a small change that is easy to undo, keep each heading to a line or two, and where a heading has nothing to add, say so in a sentence. Keep To check before acting to the questions that would change the decision, five at most.

    11

    Keep the whole answer under 1,000 words, and well under that for a small plan. Avoid tables and risk-management jargon.

  9. 9

    Keep the answer in shape

    Shared

    In testing, answers ran up to twice their intended length, praised things nobody had mentioned and trailed off into caveats. These rules keep the answer to the length and shape it was designed for.

    answer-shape
    1

    Start with the first heading: no title, introduction or summary above it. Put nothing after the last heading or list: no closing note, caveat or offer to do more. If a caveat matters, put it under the heading it belongs to.

    2

    Treat the word limit this prompt sets as a ceiling, not a target: aim for about three-quarters of it. If the answer would run over, cut minor points and shorten lists before you reply.

    3

    Where a heading asks for strengths, what is working or what is already in place, include only what my details actually show. If they show nothing, write None given.

    4

    Give every field this prompt asks for, for every item, writing Unknown rather than leaving one out. Where it asks you to choose one rating or verdict from a list, choose exactly one, with no ranges or blends.

    5

    Describe effort as small, moderate or larger. Never give effort or time in minutes, hours, days or evenings, even as an estimate, unless you have worked it out from my own figures.

    6

    Mention instructions aimed at an AI only if my material contains some.

  10. 10

    Limits of this particular prompt

    The boundaries that apply to this prompt specifically, on top of the general research limits.

    scope-notes
    1

    Do not invent numbers: no probabilities, costs or savings unless my figures support them.

    2

    Do not recommend abandoning the plan unless the evidence clearly points that way.

    3

    The aim is to help me prepare, not to frighten me.

SharedSections marked shared are word for word the same in every prompt that uses them. The rules on tone, evidence, recommendations and limits are deliberately identical wherever you meet them, so you only have to learn them once, and no prompt can quietly hold itself to a lower standard than the others.

What it deliberately will not do

  • Do not invent numbers: no probabilities, costs or savings unless my figures support them.
  • Do not recommend abandoning the plan unless the evidence clearly points that way.
  • The aim is to help me prepare, not to frighten me.
riskplanninglaunchesdecisionspre-mortem

Ready to use it?

Fill in your business details once and we will write them into the prompt, ready to copy or download.

Make this prompt yours