Counts show all available guides. Filters combine to narrow your results.
Create work & incomeGuide
Prepare a neutral interview about how people do a task
A six-question interview draft about a recent real task, with neutral probes and a clear pass option.
Illustrative resourceNot tool-testedAdults working with original, synthetic or authorized non-sensitive material
What you’re working towards
A short qualitative interview guide built around a recent concrete episode, with neutral follow-ups and optional participation. 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 six-question interview draft about a recent real task, with neutral probes and a clear pass option. Compare the result with Input; Output is a worked illustration, not text you need to paste. There are six main questions and six optional probes; 1 + 9 + 2 = 12 proposed minutes. Questions allow no purchase, no alternatives and no missing information; no improvement is assumed. No real answers, recruitment, recording, identity questions or research findings appear. 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
Draft the complete opening, exactly six main questions with one optional neutral probe each, closing and interviewer reminders from this brief. Preserve the proposed 1/9/2-minute allocation and optional participation. Ask about one actual past episode without assuming a purchase, problem or preferred answer. Do not invent participant replies or findings.
SAMPLE INPUT
Original synthetic practice input. The people, organizations, records and events below are fictional.
Fictional stationery shop research question: How do adults choose a notebook from the shop shelf during an actual recent visit?
The possible later decision is what product information to place beside the notebooks. No display change is approved.
Audience: consenting adults who remember a recent visit in which they considered a notebook; a purchase is not required. Ask about one episode, not what people think they would buy someday.
Prepare exactly six main questions with one optional neutral probe each. Cover the situation, what they looked at, their sequence of actions, alternatives if any, information used or sought, and what happened at the end.
Proposed length: 12 minutes, including 1 minute opening, 9 minutes for the six main questions and optional probes together, and 2 minutes closing. Skip probes to keep time; stop sooner whenever requested.
Boundaries: participation and every answer are optional; no names, income, identity, contact details or other personal background. Do not pitch a product, request a recording, recruit anyone or collect answers. This task prepares a guide only. No participant responses or findings exist.
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. Read every question aloud. Remove embedded praise, criticism, assumed actions and predicted buying questions. Check question count, time sum and every participation boundary against your own brief. 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
Prepare a neutral adult interview guide about one recent concrete episode of the ordinary task below. Give an optional-participation opening, my requested number of main questions with optional neutral probes, a proposed time allocation and a closing read-back instruction. Ask what happened before asking general opinions. Do not assume a purchase, problem, preference or benefit. Keep answers blank and explain what needs human review before any real recruitment or collection.
MY INPUT
Research question and possible later decision: [replace with complete non-sensitive details, or state unknown]
Adult audience and ordinary task under study: [replace with complete non-sensitive details, or state unknown]
Episode boundaries and what counts as a recent example: [replace with complete non-sensitive details, or state unknown]
Requested question count and total time including opening and closing: [replace with complete non-sensitive details, or state unknown]
Excluded topics and participation/recording/data-handling boundaries: [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
Repair leading questions
Practice neutral wording without inventing a respondent. 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 notebook brief, rewrite these three questions as neutral questions about the same recent visit: “Why were the labels confusing?”, “Would you buy more if the display were better?”, and “Which other notebook did you compare it with?” Explain the assumption removed from each. Keep the exercise separate from the six-question interview and do not supply answers.
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 stationery shop research question: How do adults choose a notebook from the shop shelf during an actual recent visit?
The possible later decision is what product information to place beside the notebooks. No display change is approved.
Audience: consenting adults who remember a recent visit in which they considered a notebook; a purchase is not required. Ask about one episode, not what people think they would buy someday.
Prepare exactly six main questions with one optional neutral probe each. Cover the situation, what they looked at, their sequence of actions, alternatives if any, information used or sought, and what happened at the end.
Proposed length: 12 minutes, including 1 minute opening, 9 minutes for the six main questions and optional probes together, and 2 minutes closing. Skip probes to keep time; stop sooner whenever requested.
Boundaries: participation and every answer are optional; no names, income, identity, contact details or other personal background. Do not pitch a product, request a recording, recruit anyone or collect answers. This task prepares a guide only. No participant responses or findings exist.
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.
Draft opening, proposed minute 0–1
“We are preparing to understand how adults choose a notebook from a shelf. If you choose to take part in a separately arranged conversation, you can skip any question or stop without giving a reason. Please leave out names and personal details. We will focus on one recent visit. This is not a sales pitch.”
Before real use, confirm the actual participation and data-handling arrangements. This sample does not authorize recruitment, recording or collecting answers.
Main questions, proposed minutes 1–10
1. Think of a recent visit when you considered a notebook here. What was happening when you began looking?
Optional probe: What were you trying to do on that visit?
2. What did you look at first?
Optional probe: What caught your attention at that point?
3. What did you do next as you considered the notebooks?
Optional probe: Can you walk me through that part in order?
4. What other options, if any, did you consider during that visit?
Optional probe: How did you compare those options, if you compared them?
5. What information did you use or look for during that visit?
Optional probe: Was there anything you looked for but did not find?
6. How did that visit end for you?
Optional probe: What, if anything, did you choose to do then?
Closing, proposed minutes 10–12
“I will briefly repeat the sequence I heard, using your words. Please correct anything I misunderstood, or pass. Is there anything about that visit you want to add before we stop?”
Leave the read-back empty until actual authorized answers exist. Do not invent a purchase or a frustration.
Interviewer reminders
Allow a pause; do not fill it with a suggested answer. “If any” leaves room for no alternatives and no missing information. Ask about the actual episode before general opinions. Avoid “What was confusing?”, “Would better labels help?” and “Would you buy this?” because they assume a problem or ask for a prediction. No answers, findings or tested interview timing are supplied.
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 polished question can still lead: “What made this frustrating?” assumes frustration.
An illustrative interview draft is not evidence about customers. Only actual authorized research can supply answers, and its limits still need review.