Counts show all available guides. Filters combine to narrow your results.
Simplify a complex taskGuide
Find who a survey result leaves out
A careful respondent-only claim and an explanation of who the recruitment method missed.
Illustrative resourceNot tool-testedAdults working with original, synthetic or authorized non-sensitive material
What you’re working towards
A coverage-and-selection critique limited to the recruitment facts, plus more careful wording of what the result supports. 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 careful respondent-only claim and an explanation of who the recruitment method missed. Compare the result with Input; Output is a worked illustration, not text you need to paste. 18/20 is 90% of respondents; the replacement sentence names the Saturday-visitor recruitment route. 20/80 is 25% of membership, not the invitation response rate; the number invited is unknown. Nonvisitors’ preferences and the other two respondents’ answers are not invented. 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 the source is missing or contradictory, leave that part unresolved and obtain the needed fact before using it.
Your starting prompt
Audit C1 against R1–R3. Show the relevant arithmetic, distinguish members, invited members and respondents, and rewrite the claim for the exact observed group. Explain coverage and voluntary-response limits in plain words. Keep unknown invitation count, remaining answers and motives unknown. Give one planning question for broader coverage without conducting outreach.
SAMPLE INPUT
Original synthetic practice input. The people, organizations, records and events below are fictional.
Complete fictional survey summary, invented for this exercise:
R1. The adult hobby club has 80 members. The survey was offered only to adult members visiting on a Saturday. Nonvisitors, including people unable to attend on Saturdays, were not invited through any other route.
R2. The number of people invited was not recorded. Participation was voluntary.
R3. Exactly 20 distinct members responded once each to the question “Would you like longer Saturday opening hours?” Of these, 18 answered Yes. The summary does not specify the other two answers.
C1. Draft headline: “90% of all members want longer Saturday hours.”
No demographic information, reasons for visiting/responding, or preferences of nonrespondents are supplied. Assess only what this recruitment summary supports. Do not estimate all-member preferences, fabricate survey answers, infer motives or claim statistical representativeness.
Return written text only. Keep this fictional and label illustrative dialogue as invented. Do not claim an actual interview, survey, learner trial or tool execution. Do not send, publish, collect responses 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 your own, authorized non-sensitive material. Expect the same kind of complete result using your inputs. Underline the invited group and the actual respondents in your source. Check that the revised claim names the actual group and uses the matching denominator. Do not let a correct percentage hide an unsupported audience claim. 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 the source is missing or contradictory, leave that part unresolved and obtain the needed fact before using it.
Your starting prompt
Review my survey claim using only the supplied recruitment facts and counts. Identify the intended population, who could be invited, who was actually invited and who responded. Calculate only rates whose denominators are known. Separate coverage gaps from possible voluntary-response differences and unknown nonresponse. Rewrite the claim for the exact supported group, preserve unknown answers, and propose one question for improving recruitment. Do not infer demographics, motives or population estimates, or invent responses.
MY INPUT
Intended population and size if known: [replace with complete non-sensitive details, or state unknown]
Recruitment method and eligibility: [replace with complete non-sensitive details, or state unknown]
Number invited, or explicitly unknown: [replace with complete non-sensitive details, or state unknown]
Distinct respondent count and exact answer counts: [replace with complete non-sensitive details, or state unknown]
Claim to assess: [replace with complete non-sensitive details, or state unknown]
Known excluded groups, unknown answers and prohibited inferences: [replace with complete non-sensitive details, or state unknown]
Use only MY INPUT for facts, names, dates, counts and constraints. Ask about essential missing information or conflicting rules instead of guessing. Do not import any practice-example values. Return the complete requested result, unresolved questions and checks tied to my input. Do not send, publish, collect responses, buy, book or change another service.
Optional: improve the result
Add a known invitation count
See which uncertainty a new fact resolves and which limits remain. This optional extension uses only the original synthetic sample. Return to the sample chat, or paste its complete Input into a new chat first. To use it with your own material, replace the source and every dependent rule, number and check explicitly.
Advanced prompt
In a separate revision of the original fictional summary, R2 is corrected to say 40 Saturday-visiting adult members were invited. Keep all other facts unchanged. Calculate the invitation response rate, retain the 18-of-20 Yes share, and explain why the all-member headline is still unsupported. Expected arithmetic: 20/40 = 50% invitation response, 18/20 = 90% Yes among respondents.
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. The people, organizations, records and events below are fictional.
Complete fictional survey summary, invented for this exercise:
R1. The adult hobby club has 80 members. The survey was offered only to adult members visiting on a Saturday. Nonvisitors, including people unable to attend on Saturdays, were not invited through any other route.
R2. The number of people invited was not recorded. Participation was voluntary.
R3. Exactly 20 distinct members responded once each to the question “Would you like longer Saturday opening hours?” Of these, 18 answered Yes. The summary does not specify the other two answers.
C1. Draft headline: “90% of all members want longer Saturday hours.”
No demographic information, reasons for visiting/responding, or preferences of nonrespondents are supplied. Assess only what this recruitment summary supports. Do not estimate all-member preferences, fabricate survey answers, infer motives or claim statistical representativeness.
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.
Check the arithmetic and the group
18 ÷ 20 × 100 = 90%. This is the share of respondents who answered Yes, not a measured share of all 80 members.
Careful replacement for C1
“Among 20 adult club members who responded to a survey offered to Saturday visitors, 18 (90%) said they wanted longer Saturday hours. This survey does not establish the preferences of all 80 members.”
Who was left out
R1 excludes members who did not visit on Saturday, including people unable to attend then. Their views may differ, but the direction or size of any difference is unknown. Do not say they oppose longer hours or explain why they did not attend.
Who chose to respond
R2 says participation was voluntary. Respondents may differ from invited nonrespondents; this is a possible selection limit, not a proven motive. Because the number invited is unknown, the invitation response rate cannot be calculated.
Keep the denominators separate
20/80 = 25% describes the fraction of membership represented by the 20 distinct respondents in this fictional record. It is not the response rate, because not all 80 were invited. The other two respondents’ answers remain unspecified, not automatically No.
Question for a future recruitment plan
How could the club offer the same optional question to members who cannot attend on Saturday, using a separately approved route? Reaching more groups could improve coverage but does not guarantee representative responses. No outreach or new collection has occurred.
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 large percentage among a selected group does not make the group representative.
Not answering Yes is not necessarily answering No. Missing response details must remain missing.