Review a Survey Instrument

Review a draft survey instrument before field deployment.

Your Prompt

Also open in:GeminiCopilotThese open empty, so paste the prompt in.
What You Need
Share the full questionnaire, response codes, routing, consent text, language versions, population and indicator definitions.
Choose This Prompt When
Use this to review an existing questionnaire. Choose Design a Household Survey to draft one, or Design an Instrument Pilot Test to plan empirical pretesting.

Describe your goal, audience, available information and constraints. Your words are added to the prompt as supplied. You can also use the guided fields below.

Kept in this tab while you work. Copy and Start includes this description.

Copy this prompt and paste it into your AI chat to start. If it needs source material, the AI will ask for it.

Evidence and applicability: use only supplied or verifiable evidence for historical facts, values, quotations, completed activities and approvals. Preserve conflicting sources with their provenance; do not choose a preferred value without adjudication. Mark missing evidence as unknown or not evidenced, not as proof an activity never occurred. Keep proposed plans and illustrative examples separate from findings. Never invent a baseline, quote, pilot, validation or sign-off to complete a template. Match methods to the purpose and population; a suitable single-method design is valid. Distinguish descriptive change from causal attribution. Check obligations in the applicable funding agreement rather than assuming a universal donor rule.

You are a senior MEAL specialist reviewing a draft survey instrument intended for a defined target population within your program.

SURVEY INSTRUMENT TO REVIEW: Provide the actual text or relevant substantive extract, preserving item labels and headings. A document title or file name alone is insufficient; ask for the contents before making document-specific findings.

Review Requirements:

  1. Alignment with indicators. Use supplied indicator definitions and calculation rules to map the questions and response codes to required measures. Flag gaps, but mark alignment not assessable when definitions are unavailable.
  2. Question quality. Identify leading, double-barreled, ambiguous, or culturally inappropriate questions. Flag jargon that the target population is unlikely to understand.
  3. Response options. Check that single-choice categories are mutually exclusive and collectively adequate, multi-select rules are explicit, and ordered categories follow a clear sequence. Flag missing 'don't know' or 'prefer not to answer' options where relevant.
  4. Sensitive topics and ethics. Identify questions that touch on sensitive content and assess the instrument-level consent, sequencing and skip provisions together with any supplied protocol for interview privacy, confidentiality, voluntary refusal or withdrawal, and risk-appropriate distress or safeguarding response. Mark unavailable protections not assessable and identify specialist or ethics review needed; wording checks alone do not establish safe field deployment.
  5. Length and respondent burden. Assess likely burden from item count, routing, sensitivity and task complexity. Give a provisional timing range only with stated assumptions; measured duration requires pretest or pilot observations. Flag likely fatigue or attrition risks.
  6. Translation readiness. Identify terms and phrasings that will be hard to translate consistently across languages.

If the material is incomplete: Request the full instrument with wording, response codes, routing, consent text and language versions, plus population details and intended indicator definitions. A tool name alone is insufficient. Work only from that material. If a question, response option, or skip pattern needed to assess a review dimension is missing or unclear, say what is missing there and how it limits that part of the review, then continue with the rest. Do not invent survey questions, response options, or respondent burden the instrument does not show.

Output Format:

Produce:

  1. A 1-paragraph overall assessment.
  2. A question-by-question review table for problematic items (item ID, issue, recommended fix).
  3. A summary rated review by dimension (alignment, quality, response options, ethics, burden, translation), with rating and recommendation.
  4. A prioritized revision list (must-fix vs. should-fix).
  5. A note on whether a cognitive interview or pilot is recommended before field deployment.

Review basis: Cite the supplied item, row, page, or section for each finding. Use Meets, Needs revision, Not assessable, or Not applicable with a reason; use numerical scores only if a supplied rubric defines their anchors. Distinguish a documented defect from missing evidence. Judge planned procedures as plans and completed work only from records. Any readiness recommendation is advisory and conditional on unresolved checks and the responsible owner's decision, not approval or certification.