Usewright
Back to results
Explore the library298 guides total · goals, work & tasks
By goal

Choose what you want to achieve.

By work or interest

Choose a setting you work or spend time in.

By task

Choose the kind of help you want.

Counts show all available guides. Filters combine to narrow your results.

Create work & incomeGuide

Draft a short feedback survey people can answer

Turn a specific club decision into optional questions, supplied answer choices and skip rules that match a codebook.

Illustrative resourceNot tool-testedPeople preparing a low-stakes feedback questionnaire for an adult club or group
What you’re working towards

A downloadable five-question paper draft and matching codebook with exact answer choices, optional paths and checked branching. No form has been published and no responses have been collected.

Download playbook .md

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.

Included example · illustrative MD file

Download the club questionnaire

Five optional questions with printed answer options and explicit skip instructions. Original synthetic draft; no collection endpoint.

Not tool-tested. Review and adapt before using it for a real project. Your browser may download this file when you choose View example file.

View example file (opens in a new tab; your browser may download the file) Download example

Source files to work with

Make a start

One step at a time.

4 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.

Set up the worked example

Open

Open a fresh text-AI chat and a plain-text editor. A codebook is a table defining each question, answer choice and next step; it contains no people’s answers. CSV means comma-separated text. Use the fictional adult-club brief; no survey service, account, recruitment or distribution is needed.

Add the sample

Download and open survey-decision-brief.md, which matches the complete brief in ‘The starting point’ (Synthetic input). Paste the whole file into steps 1 and 2, replacing their bracketed instructions. For the worked five-question pattern, keep attendance, its conditional visit-count follow-up, availability, preference and one optional open question separate. Save step 2’s questionnaire as my-survey.md, reopen it, and paste that exact text into step 3. Save the returned CSV alone as my-codebook.csv without code-fence lines; reopen it before step 4 and paste both saved files plus the brief. ‘The intended result’ (Illustrative output), club-feedback-survey.md and survey-codebook.csv are reference answers, not collected responses. For the optional advanced sample exercise, paste the complete original decision brief, saved questionnaire, saved codebook and actual branch-check report into its placeholder, even if they appeared earlier. If starting a new chat, supply all of them again; if any is missing, retrieve it or keep that exercise pending rather than infer the earlier result.

Start with the synthetic example, then adapt each prompt to your task.

01

Start with the decision and real options

Download the decision brief. Keep the decision, adult audience, supplied options and dates together; unknown recruitment and decision thresholds remain unknown.

Your starting prompt
Use only this decision brief. Restate the one decision, audience, supplied choices, dates and current uncertainty. List information that is missing rather than inventing research aims, response counts, representativeness, demographics or a decision threshold. Work with this synthetic adult-club fixture first. Do not create a live form, collect personal information or send anything.

DECISION BRIEF:
[paste survey-decision-brief.md]
Expect

A decision summary naming the adult audience, three proposed opening options, four trial weekends and what is still unknown.

Check

The only options are Saturday 10:00–12:00, Saturday 14:00–16:00 and Sunday 14:00–16:00. The four weekends run from 17–18 October through 7–8 November 2026. Recent attendance is context, not a vote weight. Recruitment, sample size and decision thresholds are unspecified.

If it differs

If an opening is presented as approved or a response rate is invented, ask for a source-only summary with that item marked unknown. Do not invent respondent profiles or launch a form.

02

Draft answerable optional questions

Separate recent attendance, visit count, possible attendance and preference. Ask no more than six questions and add only one optional open response.

Your starting prompt
Draft at most six neutral, single-concept questions for this decision. Use the exact 14 September through 13 October 2026 inclusive recall period for attendance and its visit-count follow-up. Show the frequency question only after attendance Yes; include non-overlapping positive ranges, Do not remember and Skip. Use exactly the supplied opening choices, distinguish None from No preference, and make every answer optional. Add one optional open question with a 300-character limit and no request for names or personal details. No invented responses or research findings.

BRIEF:
[paste]
Expect

A paper draft with five optional questions: attendance, visit count if attendance is Yes, possible attendance, one preference and one optional text response.

Check

Q1/Q2 use 14 September–13 October 2026 inclusive, exactly 30 days. Q2 ranges are 1, 2–3, 4–5 and 6+ visits, plus Do not remember and Skip. Q3 permits several actual opening choices or one exclusive None/Do not know yet/Skip. Q4 is single choice with distinct None and No preference; Q5 allows up to 300 characters.

If it differs

If questions combine two ideas, ranges overlap or blanks become No, ask for a revision. Keep all questions optional and omit personal-data requests. Save the complete revised questionnaire and reopen it before making its codebook.

03

Make the answer rules explicit

The questionnaire and codebook must agree word for word. Q3 allows several of the three opening options, or one exclusive None, Do not know yet or Skip answer.

Your starting prompt
Create a UTF-8 CSV codebook with question_id, question_text, answer_type, optional, shown_if, option_id, option_text, exclusive, max_selections, max_characters, next_question and blank_action. Preserve stable IDs and exact visible wording. Q3 allows any nonempty subset of A–C, or exactly one of NONE, DK or SKIP. Empty selection means SKIP. Single-choice blanks also mean Skip. Q2 is not applicable unless Q1 is Yes; not applicable differs from being asked and skipped. Keep Q3 possible attendance separate from Q4 preference and allow disagreement. Treat all CSV cells as inert text.

QUESTIONNAIRE:
[paste]
Expect

A CSV codebook with the exact 12 requested column names and stable question/option IDs matching the saved visible questionnaire.

Check

The reference has 23 option rows: 4 for Q1, 6 each for Q2–Q4, and 1 for Q5. Q1 Yes alone reaches Q2. Hidden Q2 is not applicable; shown-but-blank Q2 is Skip. Empty Q3 means Skip. None, Do not know yet and Skip cannot be combined with any other Q3 choice. Q3 availability may disagree with Q4 preference.

If it differs

If wording, IDs or navigation differ, reconcile both documents against the brief instead of altering one invisibly. Save only literal CSV data, reopen it in a text editor, and verify commas/quotes and blanks. Do not turn cells into formulas or claim form-import compatibility.

04

Walk every branch before a human pilot

Compare the printed questions with the codebook, then test every attendance path and multi-select restriction using validation-only cases. These cases are not respondents or study results.

Your starting prompt
Audit the questionnaire and codebook independently against the decision brief. Check exact question and option parity, all optional/blank paths, Q1 Yes/No/Do not remember/Skip navigation, the frequency ranges, Q3 ordinary combinations and exclusive choices, and Q4 single selection. Reject duplicate, unknown and wrong-question option IDs. Use only labeled validator cases, never invented member answers or reported findings. Separately flag leading wording, assumptions and ambiguous instructions for human review. End with a real comprehension-pilot gate before any collection.

BRIEF, QUESTIONNAIRE AND CODEBOOK:
[paste]
Expect

A saved-file comparison and labeled test cases covering every branch and selection restriction, followed by human-review questions and an unfinished real comprehension-pilot gate.

Check

Walk Q1 Yes, No, Do not remember, explicit Skip and blank. Check a permitted Q3 multi-choice, each exclusive choice alone, forbidden None-plus-option, blank, duplicate and unknown IDs. Preference despite no expected attendance is allowed. The reference’s 64 Q3 subsets and 1,080 canonical routes describe synthetic checks, not respondents or findings.

If it differs

If tests are merely described, label them planned rather than executed. Fix mismatched saved files in new revisions and repeat affected and unchanged paths. Keep real owner review and adult comprehension testing pending; do not claim bias-free wording, statistical validation, recruitment, publication or collection.

Optional: improve the result

Challenge the instrument without inventing respondents

Separate the mechanics of navigation from human understanding. A complete branch walk does not establish good sampling, comprehensibility or neutral interpretation.

Advanced prompt
Review a separate copy of the questionnaire against its original decision brief. First produce an exact question/option diff against the codebook. Then challenge No, Do not remember, Skip, a hidden Q2, a blank Q3, all three availability options, None with an option, duplicate/unknown IDs and a preference different from availability. Explain which combinations are permitted and why. Audit one concept per question, recall-period clarity and wording that presumes a positive experience. Propose a small real comprehension pilot in which adults explain what each question means; do not invent participants, answers, outcomes, sample-size validity or a bias-free certification. Keep form publication and collection as separate owner decisions.

BRIEF AND CURRENT FILES:
[paste]
Optional: use your own input

Draft questions for your own opening-options decision

Keep this route to one low-stakes opening-options decision for an adult group. Supply permitted non-sensitive facts, with no responses or contact lists. Replace the bracketed instructions, send the opening prompt and review its summary. Then send:
“Draft five optional, single-concept questions from MY CHECKED BRIEF: attendance in MY FIXED RECALL PERIOD; a positive visit-count follow-up shown only after Yes; which of MY ACTUAL OPTIONS could be attended at least once during MY TRIAL DATES; one preference among those same options; and exactly one optional open response with MY CHARACTER LIMIT. Include Do not remember and Skip where applicable, non-overlapping exhaustive positive visit ranges, exclusive None/Do not know yet/Skip for availability, and distinct None/No preference/Skip for preference. No personal-data questions. CHECKED BRIEF: [paste].”
Save as my-survey.md and reopen it.
“From MY SAVED QUESTIONNAIRE, make inert UTF-8 CSV with question_id,question_text,answer_type,optional,shown_if,option_id,option_text,exclusive,max_selections,max_characters,next_question,blank_action. Preserve exact wording and unique stable IDs. Define every ordinary and exclusive selection, blank and next-step rule. Hidden visit count is not applicable; shown but blank is Skip. Empty availability is Skip; blank free text means no supplied text, not an opinion. Availability and preference may disagree. Derive row/option counts from this questionnaire. SAVED QUESTIONNAIRE AND BRIEF: [paste].”
Save the CSV alone as my-codebook.csv and reopen it.
“Audit MY SAVED FILES against MY BRIEF. Compare exact question/option wording, IDs, date periods, ranges, optionality, character limit and navigation. Walk every attendance branch, all availability subsets for my small option set, exclusive/blank paths, preference disagreement, duplicate/unknown/wrong-question IDs and text length limits. List actual test results only if executed; otherwise provide a manual case checklist. These are synthetic validation cases, never member answers or findings. Flag ambiguous or leading wording for human review. SAVED QUESTIONNAIRE, CODEBOOK AND BRIEF: [paste].”
Check the saved files yourself, correct in new revisions and repeat the affected routes. Your number of options, ranges, dates, character limit and resulting codebook/test counts replace the sample’s values. A real owner review and adult comprehension pilot remain required before any separately approved collection. The original advanced exercise is sample-scoped until its IDs, cases and periods are adapted to your reviewed instrument. No recruiting, distribution or live form is part of this drafting route.

Your own-input prompt
Help me draft a paper feedback questionnaire for one low-stakes adult-group opening-options decision. First restate MY DECISION, adult audience, actual opening options, exact prospective trial dates, inclusive recall start/end dates, intended visit-count ranges and open-response character limit. Identify missing facts and overlap in choices/ranges; do not invent sample sizes, recruitment, thresholds or representative findings. Retain five optional single-concept questions: attendance, conditional visit count, availability, preference and one open response. Confirm which options could be attended at least once in the trial period and which one is preferred are different questions. Keep every answer optional, blank distinct from No, and hidden follow-ups distinct from skipped ones. Stop after the brief review. Do not publish a form, collect answers, recruit or message anyone.

MY DECISION BRIEF
[State the one decision and adult audience; list the actual opening day/time options with stable labels and local-time context; list every trial date/weekend; give exact inclusive recall dates, positive visit-count ranges and open-text character limit. Include any real owner-supplied constraints. Use fictional labels where possible. Do not paste responses, private information or contact lists.]

Check your own result

  • All five questions serve your decision and retain your exact options and periods; each asks one concept and is optional.
  • Your visit ranges cover positive counts without overlap; the follow-up appears only after attendance Yes.
  • The saved questionnaire and codebook agree in every label, ID, selection, blank and navigation rule; counts come from your files.
  • Availability and preference may disagree. Test cases are not responses; owner review and a real comprehension pilot remain pending before separately approved collection.
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.

The starting point

Synthetic input
# Club opening-options decision brief

Original synthetic fixture. The club, choices and dates are invented for guide authoring. There are no members' answers, contact details, live forms or collected results in this package.

Decision: choose one recurring weekend opening option for a four-week trial at the fictional adult hobby club. The supplied options are Saturday 10:00–12:00, Saturday 14:00–16:00 and Sunday 14:00–16:00, all in the club's local clock time. The trial would cover the weekends of 17–18 October, 24–25 October, 31 October–1 November and 7–8 November 2026. No option is approved, and no opening, invitation or booking is authorized.

Audience: adult club members, including people who did not attend recently. Current uncertainty: which supplied option people could attend at least once during these four weekends, and which single option they prefer. Recent attendance provides context, not a weighting rule or measure of commitment. There is no supplied sample, recruitment method, expected response rate, representativeness claim or decision threshold.

Instrument limits: no more than six questions, one concept per question, all answers optional. Use the fixed 30-day recall period 14 September through 13 October 2026, inclusive. Ask about attendance in that period and show one frequency follow-up only after Yes. Use non-overlapping visit-count ranges. Ask availability as a multiple-selection question with mutually exclusive None, Do not know yet and Skip options. Ask one preference question with the three real options, None and No preference. Add exactly one optional open response. Do not request names, contact details, membership identifiers, health, finances, protected traits or information about children.

Q3 availability and Q4 preference are separate: people may express a preference even if they currently expect to attend none. Do not silently reject or recode such a combination. All blank single-selection answers mean Skip. An empty Q3 selection means Skip. Skipped Q2 after anything other than Q1 Yes is not applicable, which is distinct from an asked Q2 being skipped. The optional text question can stay empty; do not infer an opinion from an empty response.

Make a printable questionnaire and matching UTF-8 codebook with stable question and option IDs, wording, answer type, permitted selections and navigation. No form publication, mailing or collection. A human owner should review the decision, dates and wording, then run a small real comprehension pilot before deciding whether to collect answers. A fixture validator is not statistical validation and cannot establish the absence of bias.

Copies text only. For image or file tasks, use the source files named in the steps too.

Download source .txt

The intended result

Illustrative output
# Club opening-options questionnaire

Illustrative paper draft for adult club members. Do not collect answers with this sample before human review and a real comprehension pilot. No option has been approved.

The club is considering one recurring opening option for four weekends: 17–18 October, 24–25 October, 31 October–1 November and 7–8 November 2026. Times use the club’s local clock. We want to understand possible attendance and preferences.

Every question is optional. You can skip any question or stop. Do not write your name or contact details. A blank choice means Skip, not No. For Q2, follow the Q1 instruction; a question not shown is not applicable.

For Q1 and Q2, the fixed last-30-days period is 14 September through 13 October 2026, inclusive. For Q3 and Q4, consider only the four weekends listed above.

## Q1. Did you attend the club at least once during 14 September through 13 October 2026 (inclusive)?

Choose one. Optional; leaving blank means Skip. Yes goes to Q2; every other choice goes to Q3.

- [ ] [Q1_YES] Yes → Q2
- [ ] [Q1_NO] No → Q3
- [ ] [Q1_DK] Do not remember → Q3
- [ ] [Q1_SKIP] Skip this question → Q3

## Q2. How many separate club visits did you make during 14 September through 13 October 2026 (inclusive)?

Answer only if Q1 is Yes. Choose one. Optional; leaving blank means Skip. Then go to Q3.

- [ ] [Q2_ONE] 1 visit
- [ ] [Q2_TWO_THREE] 2–3 visits
- [ ] [Q2_FOUR_FIVE] 4–5 visits
- [ ] [Q2_SIX_PLUS] 6 or more visits
- [ ] [Q2_DK] Do not remember
- [ ] [Q2_SKIP] Skip this question

## Q3. Which opening options could you attend at least once during the four weekends from 17 October through 8 November 2026?

Select all options A–C that apply, or select exactly one of None, Do not know yet or Skip. Do not combine any of those last three with another choice. Optional; leaving all blank means Skip. Then go to Q4.

- [ ] [Q3_A] Saturday 10:00–12:00
- [ ] [Q3_B] Saturday 14:00–16:00
- [ ] [Q3_C] Sunday 14:00–16:00
- [ ] [Q3_NONE] None of these options
- [ ] [Q3_DK] Do not know yet
- [ ] [Q3_SKIP] Skip this question

## Q4. Which one opening option would you prefer for the four weekends from 17 October through 8 November 2026?

Choose one. Optional; leaving blank means Skip. No preference means you are not choosing one option over the others; None means you would prefer none of the supplied options. Then go to Q5.

- [ ] [Q4_A] Saturday 10:00–12:00
- [ ] [Q4_B] Saturday 14:00–16:00
- [ ] [Q4_C] Sunday 14:00–16:00
- [ ] [Q4_NONE] None of these options
- [ ] [Q4_NO_PREF] No preference
- [ ] [Q4_SKIP] Skip this question

## Q5. What, if anything, should the club consider when choosing among these opening options?

Optional. Write at most 300 characters or leave blank. Do not include names, contact details or personal information. Then finish.

- [Q5_TEXT] Optional text; blank is allowed

Response: ____________________________________________________________

______________________________________________________________________


## Finish

Thank you for considering the options. This sample contains no collection destination and must not be treated as a published survey.

CODEBOOK AND CHECKED SCOPE
The matching survey-codebook.csv has 23 stable option rows across five questions. An independent local parser checked exact questionnaire/codebook parity, all 64 Q3 subsets, 10 canonical Q3 choices and 1,080 complete canonical routes. Sixteen deliberate corruptions were rejected. These are synthetic validator paths, not member responses or survey results. Text wording was separately reviewed for single concepts, fixed periods, optionality and non-overlapping ranges. No statistical validation, absence-of-bias guarantee, human comprehension pilot, form collection, AI execution or time-saving measurement is claimed.
Download result .txt
You’re the final check

Check the worked example.

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.

  • Using a vague recent period or overlapping visit ranges that people cannot answer consistently.
  • Treating a blank answer as No or treating a skipped frequency question as zero visits.
  • Allowing None together with an opening option in a multi-select answer.
  • Calling a locally checked questionnaire unbiased, statistically validated or already understood by respondents.

What has been checked?

Documentation
No dated source review recorded.
Included files
Scoped checks passed on 2026-10-14. Fixture checks; File parsing. See scope below.
AI workflow
Not run in a recorded consumer-AI workflow.
Time savings
Time savings not measured
Read the scope and evidence

club-feedback-survey.md

2026-10-14 · semantic fixture · passed

Local exported-fixture checks only. No human comprehension pilot, respondent data, provider access, form compatibility or AI execution was checked.

  • UTF-8 exported file read successfully
  • File SHA-256 recorded after validation
  • Five questions and 23 exact option labels match independent controls and CSV
  • All optional, fixed-period and visible skip/multiple-selection instructions checked
  • 1,080 canonical complete paths walked; 16 deliberate file mutations rejected

Environment: Python 3.12.14 standard library on Linux-6.18.44-x86_64-with-glibc2.41

SHA-256: ef63b44c6286d8dc76b7d6efc29b2bbc2beb8b743ac3022b28cfb7f1d52be679

survey-codebook.csv

2026-10-14 · parser · passed

Local exported-fixture checks only. No human comprehension pilot, respondent data, provider access, form compatibility or AI execution was checked.

  • UTF-8 exported file read successfully
  • File SHA-256 recorded after validation
  • CSV header, 23 rows, widths, round-trip and inert cells checked
  • 64 multi-select inputs: 11 accepted including blank alias, 53 rejected; 10 canonical choices
  • Single-choice, duplicate/unknown ID and navigation constraints checked

Environment: Python 3.12.14 standard library on Linux-6.18.44-x86_64-with-glibc2.41

SHA-256: bbf1420c1f3ac2f828b8e8dec495ceb51f2885f3ff8d4d9b20e2e6587dc00c85

survey-decision-brief.md

2026-10-14 · semantic fixture · passed

Local exported-fixture checks only. No human comprehension pilot, respondent data, provider access, form compatibility or AI execution was checked.

  • UTF-8 exported file read successfully
  • File SHA-256 recorded after validation
  • Original decision, three options, fixed periods and no-collection boundary supplied; editorial source review only

Environment: Python 3.12.14 standard library on Linux-6.18.44-x86_64-with-glibc2.41

SHA-256: ba0d50694e3f3436d8821146e83fa2fc45a02060f6e407603fff4b9d16cb1694

Keep going
Back to the library
  1. Simplify a complex taskGuide

    Find themes in customer feedback without inventing consensus

    A downloadable theme ledger that preserves source IDs and exact excerpts, counts unique codable comments transparently and keeps excluded or unclear rows visible.

  2. Communicate clearlyPlaybook

    Turn a fixed shop policy into a faithful customer FAQ

    A complete eight-question FAQ and an owner-review list, traceable to a fixed source policy.

  3. Build a workflowDry run recipe

    Design a form-to-Slack handoff with a human gate

    A complete simulated intake queue, message preview and approval/error test cases. No form or Slack integration is connected.

Copy these instructions

Your browser blocked automatic copying. Select the text below and copy it.