Prompt pack4 steps11 prompts
Design & Analyze a Survey
Use this when you need numbers from many people, not quotes from a few. Write the decision first, then the questions, then field, clean, and report.
01Goals and questions
Name the decision the survey will inform. Then write questions and audit them for leading wording, mixed scales, and length.
- ResearchSurvey Question AuditorQuality-check a draft survey before launch: leading language, double-barreled items, scale mismatches, bias, order effects, and more. Pairs with Survey Question Generator for write-then-audit workflows.
- ResearchResearch Question SharpenerTurn a vague or bloated stakeholder question into scorable, method-mapped research questions with prioritization and out-of-scope flags. Use before writing a discussion guide or survey.
- ResearchSurvey Question GeneratorDesign effective, unbiased survey questions that yield actionable insights.
02Field the survey
Who, how many, which channel. Cognitive-pretest on a handful of people before the full send. Then launch and remind.
- ResearchSurvey Fielding KitLaunch package for a survey: who to send to, quotas and implied send volume, invitation, 3-day and 7-day reminders, thank-you, and channel variants. Not a generic email prompt.
- ResearchSurvey Cognitive PretestTurn a draft survey into a 5-person think-aloud protocol: what to listen for, likely misreads, time estimate, and rewritten items before you field. Use after Survey Question Auditor, before the Fielding Kit.
- ResearchParticipant Screener Survey BuilderDraft a recruitment screener with intro copy, behavioral and qualifying items, explicit disqualifiers, routing notes, and recruiter guidance. Goes deeper than a high-level recruitment plan.
- ResearchParticipant Consent & Session CommsPlain-language consent and logistics: recording, data use, how to stop, incentive, and calendar copy. Variants for interviews, usability tests, surveys, and diaries.
03Clean and analyze
Drop junk and straight-liners, code open ends, then run the analysis. Do not write insights from the raw export.
- ResearchSurvey Data Quality & Open-End CoderBefore analysis: exclusion rules for speeders, straightliners, and junk; then a codebook for open-ends with example recodes. Hand off a clean file to Survey Analysis Framework. Does not invent statistics.
- ResearchSurvey Analysis FrameworkAnalyze survey data to extract design insights, identify patterns, and generate actionable recommendations.
- ResearchResearch Insight Statement WriterTurn themes and observations into decision-ready insight statements (Observation, Pattern, Implication, Recommendation) plus a short exec "So What" summary. Use after synthesis or affinity output.
04Report findings
Lead with what the numbers mean for the decision. Charts in the appendix if they help. Do not start with methodology.
Frequently asked questions
How long should the survey be?
Five to ten minutes on a phone. Cut questions that will not change a decision. If you need stories, interview instead of stuffing open boxes at the end.
Do I need a hundred responses?
For a split by segment, yes, around there. For a directional pulse, fewer is fine if you do not treat it like a census. If you cannot reach the right people, do not field it.
We already did interviews. Do we still survey?
Yes, when you need counts on questions you already know. No, if you are still guessing what to ask. That is still a study.