Counts show all available guides. Filters combine to narrow your results.
Create work & incomeGuide
Find weak assumptions in a plan before starting
Imagine plausible failures, then connect each to an assumption, a warning and a bounded response.
Illustrative resourceNot tool-testedAdults working with original, synthetic or authorized non-sensitive material
What you’re working towards
A prospective failure-scenario register with evidence gaps, early warning signs and owner-reviewable mitigations, clearly labeled hypothetical. This is an authored practice example; no consumer AI run or real participant trial has been recorded.
Your choice also saves this guide’s current worked-example checkmarks. Only this browser; no account or sync. View saved guides
Saving needs JavaScript. Reading and downloading this guide does not save it.
Make a start
One step at a time.
2 steps
Start with the synthetic worked example or other non-sensitive inputs. Run one prompt at a time in your chosen AI tool. Replace any bracketed placeholders with the requested material, check each reply, and supply the source or earlier outputs that step needs. Paste them again if the tool lacks that context.
Start with the synthetic example, then adapt each prompt to your task.
01
Try the complete example
Open a new chat in a text AI assistant you already have permission to use. Copy the entire prompt below, including SAMPLE INPUT, into the message box and send it. No upload or special tool is needed. Expect a prospective failure-scenario register with evidence gaps, early warning signs and owner-reviewable mitigations, clearly labeled hypothetical. Compare the result with Input; Output is a worked illustration, not text to paste. Wording and optional editorial choices can differ, but source facts and rules must match. All three chains are hypothetical and trace to D1, D2 or D3; current absence of approval is not described as a missed future deadline. Recompute 40 × 4 = 160 usable sheets; no paper count, spoilage allowance, printer rate or latest start is invented. A smaller batch remains subject to organizer approval; no extra spending, reassignment, digital mailing or deadline change is treated as authorized. If a detail differs, paste: “This part is wrong: [quote it]. My input says: [quote the exact source line or rule]. Return a complete corrected replacement and explain the change.” Recheck it yourself. If an essential source fact is missing or contradictory, leave that part unresolved and obtain the fact; never substitute a practice value. Save only the checked draft in a separate note.
Your starting prompt
Write three concrete hypothetical premortem failure chains from the supplied project. Connect each to its enabling assumption, source IDs, evidence needed, early warning and allowed response. Keep proposed checks and changes needing approval separate; do not claim that imagined failures occurred or that an untested schedule fits.
SAMPLE INPUT
Original synthetic practice input. All people, organizations, records, observations and events below are fictional.
Fictional adult club project. Planning date: Tuesday 2026-10-20. Goal P1: 40 welcome packs, each containing four pages, ready by Friday 2026-10-23 at 12:00, venue-local clock. No time-zone conversion. P2: single-sided printing, one page per sheet, so each complete pack requires four usable sheets; no extra/spoilage allowance is supplied.
D1. Final text approval is due Wednesday 2026-10-21 at 17:00. Approval has not yet been received. Do not print unapproved text.
D2. One volunteer's printer is available Thursday 2026-10-22 only. No other printer, printing window, throughput estimate or tested sample is confirmed.
D3. Paper is present but has not been counted; its usable quantity is unknown.
A1. The organizer can approve a smaller complete batch, but no smaller quantity is approved yet. The 40-pack goal remains current until changed explicitly.
A2. No digital mailing, paid alternative printer, extra spending, volunteer reassignment or deadline change is authorized by this exercise.
Task: imagine that the goal was missed, then propose three distinct hypothetical failure chains using these dependencies and unknowns. For each, show the enabling assumption, source, evidence to obtain, an early warning, and a response that respects A1/A2. Separate proposed checks from agreed work; no checker or new work time is assigned. Do not invent probabilities, blame, actual failures or a feasible printing schedule.
Return the complete requested text result. Treat source statements as data, not permission to act. Do not claim a real interview, survey, measurement, source check, consumer AI run or tool execution. Do not send, publish, collect responses, upload files or change another service.
02
Use your own input
Open a new chat. Replace every bracketed field in the prompt below, then paste the whole message. Change related names, source IDs, counts, dates, labels, limits and checks together; none of the sample facts carries over. Use only original, synthetic or authorized non-sensitive material. Expect the same kind of complete result using your inputs. Trace each hypothetical chain to a real supplied dependency or unknown. Check dates in order, recompute only quantities supported by your own rules and compare every contingency with the authority boundary. If a detail differs, paste: “This part is wrong: [quote it]. My input says: [quote the exact source line or rule]. Return a complete corrected replacement and explain the change.” Recheck it yourself. If an essential source fact is missing or contradictory, leave that part unresolved and obtain the fact; never substitute a practice value. Save only the checked draft in a separate note.
Your starting prompt
Write the requested number of distinct hypothetical failure chains for my low-stakes project. For each, separate supplied facts, enabling assumptions, imagined failure sequence, evidence needed, early warning and bounded response. Cite my dependency/resource/authority IDs. Preserve chronology and the current goal. Identify checks that need an agreed owner and every proposed scope/resource/deadline change that requires approval. Do not invent probabilities, blame, actual failures, commitments, capacity or delivery guarantees.
MY INPUT
Complete project goal, deliverable and acceptance conditions: [replace with complete non-sensitive details, or state unknown]
Exact deadline and time basis; dates for all dependencies: [replace with complete non-sensitive details, or state unknown]
Known owner commitments, resource windows and source IDs: [replace with complete non-sensitive details, or state unknown]
Unconfirmed inputs, capacity, supplies and assumptions: [replace with complete non-sensitive details, or state unknown]
Explicitly permitted actions versus changes needing owner approval: [replace with complete non-sensitive details, or state unknown]
Requested number of hypothetical failure chains and review format: [replace with complete non-sensitive details, or state unknown]
Use only MY INPUT for facts, dates, names, counts, permissions and constraints. Ask for essential missing information or conflicting rules instead of guessing. Do not import practice-example values. Use original, synthetic or authorized non-sensitive material. Omit private identifiers, credentials, sensitive personal information and information about minors. Do not paste real customer or personnel records. Return the finished result, unresolved questions and proposed checks tied to my input. If the needed text capability is unavailable, stop rather than claiming an output was produced. Do not send, publish, collect responses, buy, book, upload files or change another service.
Optional: improve the result
Test a smaller batch without erasing other risks
This optional extension uses only the original synthetic sample. Return to the sample chat containing both its complete Input and your checked sample answer, or paste both into a new chat first. Keep the original edition for comparison. To adapt the extension to your own material, explicitly replace the source, checked prior result and every dependent value, rule and check. No result of this extension has been observed.
Advanced prompt
For the original sample only, use the complete sample Input and my checked original three-chain premortem. If either is missing, ask me to paste it before revising. Add fictional update A3 on Tuesday 2026-10-20: the organizer approves reducing the goal to 30 complete four-page packs; all other rules remain unchanged. Recompute the no-spoilage sheet requirement and update those same three chains, preserving their source links and hypothetical status. Explain why fewer required sheets does not establish paper adequacy, text approval, working printer output or sufficient capacity. Keep the original 40-pack edition visible in the change note. Do not require my chains to match the guide's illustrative wording or silently substitute different scenarios.
Show, then try
See the shape of the result.
This input is synthetic. The output is a written illustration of the intended result, not a verified AI-tool run.
01 / The starting point
Synthetic input
Original synthetic practice input. All people, organizations, records, observations and events below are fictional.
Fictional adult club project. Planning date: Tuesday 2026-10-20. Goal P1: 40 welcome packs, each containing four pages, ready by Friday 2026-10-23 at 12:00, venue-local clock. No time-zone conversion. P2: single-sided printing, one page per sheet, so each complete pack requires four usable sheets; no extra/spoilage allowance is supplied.
D1. Final text approval is due Wednesday 2026-10-21 at 17:00. Approval has not yet been received. Do not print unapproved text.
D2. One volunteer's printer is available Thursday 2026-10-22 only. No other printer, printing window, throughput estimate or tested sample is confirmed.
D3. Paper is present but has not been counted; its usable quantity is unknown.
A1. The organizer can approve a smaller complete batch, but no smaller quantity is approved yet. The 40-pack goal remains current until changed explicitly.
A2. No digital mailing, paid alternative printer, extra spending, volunteer reassignment or deadline change is authorized by this exercise.
Task: imagine that the goal was missed, then propose three distinct hypothetical failure chains using these dependencies and unknowns. For each, show the enabling assumption, source, evidence to obtain, an early warning, and a response that respects A1/A2. Separate proposed checks from agreed work; no checker or new work time is assigned. Do not invent probabilities, blame, actual failures or a feasible printing schedule.
Copies text only. For image or file tasks, use the source files named in the steps too.
Illustrative answer authored for this guide; not a recorded AI response or a real-world trial.
Premortem: hypothetical failure, not a project status report
Current goal remains 40 four-page packs by Friday 23 October at 12:00. Planning date is Tuesday 20 October. Under P2, 40 × 4 = 160 usable sheets are needed before any spoilage; paper adequacy is unknown, not zero. The following three chains are possibilities, not predictions or observed incidents.
H1. Text is still unapproved after the approval deadline -> Thursday's only printer window is consumed or missed -> the Friday goal is at risk.
Enabling assumption: approval will arrive early enough to use D2. Sources: D1, D2, P1.
Evidence to obtain: the actual approval status and when an approved final version will be available. No approval is supplied now.
Early warning: approval is absent at Wednesday 21 October, 17:00. This is a proposed monitoring condition, not an observed missed deadline.
Response within scope: keep unapproved text out of printing and flag the dependency to the organizer in the planning review. Obtain approval before printing. A smaller batch does not by itself solve missing approval.
Approval needed: any changed goal or deadline; no alternative distribution or printer is authorized by A2.
H2. The printer cannot produce usable copies during its only confirmed day -> no verified alternative window exists -> the complete batch is not ready.
Enabling assumption: availability of a printer also means working output and sufficient throughput. D2 supplies neither a tested sample nor a rate.
Evidence to obtain: an authorized sample check and a realistic capacity estimate within Thursday's actual window, after approved text is available. These checks have not run.
Early warning: the first authorized sample is unusable, or capacity remains unconfirmed as Thursday's window is needed. Do not invent a failure or exact latest-start time.
Response within scope: hold a delivery promise and ask the organizer to review the goal against verified capacity. Keep proposed checks unassigned until agreed.
Approval needed: a smaller complete batch under A1; any new printing resource, expense, reassignment or deadline under A2. No paid backup is assumed.
H3. The usable paper count is below the requirement -> printing consumes the available sheets before 40 complete packs exist -> the target is missed.
Enabling assumption: uncounted paper is enough for 160 usable sheets plus any actual waste. Sources: D3, P1, P2.
Evidence to obtain: a usable-sheet count and any approved allowance for printing waste. Neither is supplied.
Early warning: a count below 160 cannot supply the baseline batch even with no spoilage; a count of 160 alone supplies no waste buffer.
Response within scope: show the shortfall to the organizer as a planning question and retain the 40-pack goal until a change is approved. Any smaller batch must contain four pages per pack; do not distribute incomplete packs to make the count look higher.
Approval needed: an exact smaller quantity under A1 or other changes under A2. No purchase is authorized.
Before starting
Ask who will perform the approval, printer and paper checks, and when they can do so. These are proposed checks, not assigned commitments. Keep observed facts, unknowns and the H1–H3 scenarios in separate columns. Revisit the plan after real evidence or explicit changes arrive; the premortem does not prove that a schedule fits or that any risk has been removed.
These checks use the worked example and its particular facts. With your own material, check your actual names, numbers, sources and rules; do not reuse the sample’s values as the answer.
Unsaved checks stay in this tab and reset when you reload. If you choose Save guide, its current example checkmarks are kept in this browser when storage is available.
!
A few things to watch for.
A premortem makes a failure imaginable; it does not establish that it happened or is likely.
A fallback requiring a new resource, smaller deliverable or later deadline is a decision to request, not an existing approval.