Counts show all available guides. Filters combine to narrow your results.
Simplify a complex taskGuide
Turn a broad topic into a question your sources could answer
A bounded research question tied to available documents, with an empty evidence-capture sheet.
Illustrative resourceNot tool-testedAdults working with original, synthetic or authorized non-sensitive material
What you’re working towards
A bounded research question, inclusion/exclusion criteria and evidence-needed checklist, without claiming the research has been done. 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 bounded research question tied to available documents, with an empty evidence-capture sheet. Compare the result with Input; Output is a worked illustration, not text you need to paste. Every part of the question points to I1–I3 for wording or N1–N3 for explicitly recorded reasons. Signs missing from one event remain in scope; costs, environmental impact and visitor preferences are excluded. The capture sheet stays blank; actual inventories have not been read or classified. 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
Use the complete source catalogue to narrow the broad topic to one answerable document-comparison question. Return the question, a question-part-to-source map, inclusion and exclusion rules, evidence needed and an unanswered capture sheet. Ask only about reasons explicitly recorded in the notes. Keep exact-string versus approved-normalization rules open. Do not answer the research question or invent source contents.
SAMPLE INPUT
Original synthetic practice input. The people, organizations, records and events below are fictional.
Fictional adult club’s broad topic: reusable event signs. Purpose: help the club choose which sign wording to consider reusing; no future wording has been approved.
This is a scoping exercise. The complete source catalogue below describes the available materials; their actual inventory rows and note contents have not been pasted or analyzed.
I1: sign inventory for 5 April 2026, with a stable sign-purpose ID and the exact printed wording for each sign used at that event.
I2: equivalent inventory for 3 May 2026, using the same sign-purpose IDs.
I3: equivalent inventory for 7 June 2026, using the same sign-purpose IDs.
N1, N2, N3: setup notes for the corresponding events. They may record reasons for wording changes, but completeness is not established. A missing reason must remain unknown.
Scope: these three club events and text wording only, including a sign that is absent from one inventory. Identical wording across observed events may be a candidate for reuse; it does not prove suitability for every future event.
Available time for a later first pass: 30 minutes. Stop and narrow the scope if the full sources do not fit. No visitor interviews, costs, environmental measurements, durability tests, visitor comprehension data or personal information are available. Do not fetch documents, invent their contents, answer the eventual research question or claim research has been completed. Need one research question, inclusion/exclusion rules, evidence-needed checklist and an unanswered capture sheet.
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. For each phrase in your question, point to a source that could supply the answer. Remove unsupported cost, impact or motive questions. Check that proposed evidence collection is still a plan and unanswered fields have not been filled with imagined findings. 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
Turn my broad topic into one bounded question that the named available source types could answer. Map each part of the question to needed evidence, define inclusion/exclusion rules, retain possible absences and unknowns, and provide an unanswered capture sheet. Distinguish recorded reasons from actual causes. Keep missing source contents and authority unresolved. Respect the supplied time and scope limits; if the material may not fit, propose a narrower scope for approval rather than silently excluding evidence. Do not claim the research has been done or answer from invented source contents.
MY INPUT
Broad topic, purpose and adult audience: [replace with complete non-sensitive details, or state unknown]
Complete catalogue of available sources and what each contains: [replace with complete non-sensitive details, or state unknown]
Source contents actually supplied, or explicitly not yet inspected: [replace with complete non-sensitive details, or state unknown]
Place, period, objects and comparison boundaries: [replace with complete non-sensitive details, or state unknown]
Available time and narrowing/stop rule: [replace with complete non-sensitive details, or state unknown]
Unavailable evidence and excluded personal data: [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
Remove an unavailable source type
See how the question must shrink when evidence is absent. 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
For the original source catalogue, suppose N1–N3 are unavailable and only I1–I3 can be obtained. Rewrite the research question and capture sheet so they ask only about exact wording and presence/absence across the three events. State which part has been removed and why. Do not invent reasons for differences.
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.
Fictional adult club’s broad topic: reusable event signs. Purpose: help the club choose which sign wording to consider reusing; no future wording has been approved.
This is a scoping exercise. The complete source catalogue below describes the available materials; their actual inventory rows and note contents have not been pasted or analyzed.
I1: sign inventory for 5 April 2026, with a stable sign-purpose ID and the exact printed wording for each sign used at that event.
I2: equivalent inventory for 3 May 2026, using the same sign-purpose IDs.
I3: equivalent inventory for 7 June 2026, using the same sign-purpose IDs.
N1, N2, N3: setup notes for the corresponding events. They may record reasons for wording changes, but completeness is not established. A missing reason must remain unknown.
Scope: these three club events and text wording only, including a sign that is absent from one inventory. Identical wording across observed events may be a candidate for reuse; it does not prove suitability for every future event.
Available time for a later first pass: 30 minutes. Stop and narrow the scope if the full sources do not fit. No visitor interviews, costs, environmental measurements, durability tests, visitor comprehension data or personal information are available. Do not fetch documents, invent their contents, answer the eventual research question or claim research has been completed. Need one research question, inclusion/exclusion rules, evidence-needed checklist and an unanswered capture sheet.
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.
Proposed research question
“Across the club’s events on 5 April, 3 May and 7 June 2026, which sign-purpose IDs have unchanged wording in all three inventories, which have changed or absent wording, and what reasons for changes are explicitly recorded in the corresponding setup notes?”
Why these sources can address it
- Exact wording and presence/absence → I1, I2, I3, matched by the supplied stable sign-purpose ID.
- Recorded reasons only → N1, N2, N3. If notes give no reason or conflict, mark that rather than answering why from imagination.
- Candidate wording for later reuse → a review decision based on the comparison, not proof of future suitability.
Include
All sign-purpose IDs appearing in any of I1–I3; the exact wording for each event; explicit absence where an ID is missing; source references for each value; relevant recorded reasons in N1–N3. Keep capitalization and punctuation differences visible until the owner defines whether they count as meaningful changes.
Exclude
Other events; material durability; costs or savings; environmental impact; visitor comprehension or preference; personal data. The source catalogue supplies no evidence for those questions.
Evidence needed before the first pass
1. Obtain the complete authorized I1–I3 inventories and confirm the stable IDs are used consistently.
2. Obtain the matching N1–N3 notes and identify actual references for reasons; record missing or conflicting notes.
3. Agree whether the task compares exact strings or also allows explicitly approved display-only differences. Until then, keep every difference visible.
4. Confirm whether the full materials fit the 30-minute first-pass budget. If not, ask the owner to approve a narrower set before excluding signs.
Unanswered capture sheet, repeat one blank row per supplied sign-purpose ID
sign-purpose ID: ______
I1 exact wording or absent + source reference: ______
I2 exact wording or absent + source reference: ______
I3 exact wording or absent + source reference: ______
comparison under agreed rule: ______
recorded reason + N-source reference, or not recorded: ______
remaining question for owner: ______
Status
This is a research plan. No sign has been classified as reusable, no inventory has been analyzed and no actual reason for a wording change has been reported.
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.
“Why did it change?” is too strong when the notes can support only “What reason was recorded?”
A repeated text may be a reuse candidate without being suitable for an unexamined future event.