HomeCasa Prompts

Analyze survey results with open and closed questions

Analyze your survey properly: response cleaning, percentages and top-2-box, segment cross-tabs with small-sample warnings, themes from open-ended answers and clear limitations. Designed for ChatGPT, Claude, Gemini and Microsoft Copilot. It includes 5 customizable variables and you can copy it for free in one click.

Intermediate · Text · Pending editorial review

Designed for:

Prompt

Act as a market researcher experienced in survey analysis. You present careful conclusions and never generalize beyond what the sample allows.

Context:
- Survey goal: {{goal}}
- Questions and type of each (single choice, multiple choice, scale, open-ended): {{questions}}
- Number of responses and how they were collected: {{responses}}
- Data (a summary per question or pasted rows, no personal data): {{data}}
- Who the analysis is for: {{audience}}

If the sample size is missing or it is unclear how scales were coded, ask me before analyzing.

Deliverables:
1. Data preparation: which responses to exclude (incomplete, duplicate, speeders) with an explicit rule, and scale recoding.
2. Results per question: valid n, percentages, and for scales the mean, median and top-2-box.
3. Cross-tabs by the most relevant segments, flagging any group with fewer than 30 responses where a difference is not reliable.
4. Open-ended answers: a codebook of 5-8 themes, number of mentions per theme and 1-2 verbatim quotes per theme (only real quotes from the data).
5. Key findings ranked by importance to the goal, with a confidence level for each.
6. Limitations: selection bias, non-response, question wording, sample size.
7. Recommendations and questions for the next survey.
8. Recommended charts for each question type.

Constraints:
- Do not invent answers, quotes or percentages: use [FILL IN] where data is missing.
- Results describe the people who responded, not necessarily the whole population.
- If you see personal data, recommend removing or anonymizing it.

Format: tables per question, a themes table and a 5-point executive summary at the top.

How to use it

Export the responses from your survey tool and remove names, emails and phone numbers before pasting. If there are many rows, paste a summary per question plus all open-ended answers.

Usage example

Goal: measure satisfaction with a meal delivery service · 10 questions (3 scales from 1 to 5, 1 open-ended) · 412 responses by email · Audience: product team.

Sample output

Executive summary

  1. 63.8% of respondents are satisfied (4-5) with the service.
  2. 12.9% are dissatisfied (1-2): the group to mine for churn reasons.
  3. Mean satisfaction 3.69 out of 5; median 4.
  4. 85% order weekly or monthly; only 15% order less often.
  5. Churn reasons depend on Q3, not yet provided: [FILL IN].

Q1 · Overall satisfaction (n = 412)

ScoreResponses%
1184.4%
2358.5%
39623.3%
417041.3%
59322.6%

Mean = (18·1 + 35·2 + 96·3 + 170·4 + 93·5) / 412 = 1,521 / 412 = 3.69 · Top-2-box = 263 / 412 = 63.8%

Q3 · Open-ended themes

ThemeMentionsVerbatim quote
[FILL IN after coding][FILL IN]Real quotes from the data only

Limitations

  • Surveyed active customers only: people who already left are missing, so churn reasons will be under-represented.
  • Results describe the people who responded, not the whole customer base.

…

Key facts

Category
Data management · Data analysis
Output type
Text
Level
Intermediate
Designed for
ChatGPT, Claude, Gemini and Microsoft Copilot
Verified in
Pending editorial verification
Variables
Survey goal, Questions and types, Responses and collection, Data and Audience
Language
English
Price
Free, no sign-up
Updated
Nov 7, 2026

Frequently asked questions

What is top-2-box?

It is the share of people who pick the two highest options on a scale, for example 4 and 5 on a 1-5 scale. It is easier to communicate than an average.

How many responses do I need to compare groups?

There is no magic number, but with fewer than about 30 responses per group, differences are usually unreliable. The prompt flags this on every cross-tab.

What is this prompt for?

Analyze your survey properly: response cleaning, percentages and top-2-box, segment cross-tabs with small-sample warnings, themes from open-ended answers and clear limitations.

Which AI tools does it work with?

It is designed for ChatGPT, Claude, Gemini and Microsoft Copilot. We have not verified it in these tools yet, so results may vary between them.

How do I customize the prompt?

Click “Customize” and fill in the variables (Survey goal, Questions and types, Responses and collection, Data and Audience). The text updates instantly and you can then copy it in one click. Values are stored only in your browser.

Do I need experience to use it?

It is intermediate: it helps to know the topic so you can provide good context and review the result critically.

Is this prompt free?

Yes. Every HomeCasa Prompts prompt is free, with no sign-up or subscription. You can also use them in professional projects.

Can I trust the AI output?

Treat it as a high-quality draft: always check data, figures and important claims before publishing or making decisions.

Related prompts