Analyse agreement scale answers correctly

Prompt that analyses scale answers with distributions instead of misleading averages. Paste it into an AI tool of your choice, which then analyses the scale answers.

Topic: Spreadsheets & data
Type: Prompt
Level: Intermediate
Time: about 15 min

Results depend on the tool, the model and what you enter.

Result preview

Example: written by our editors, not real AI output.

| Item | Agree | Neutral | Disagree | n | | Clear goals | 72% | 18% | 10% | 84 | | Workload is fine | 41% | 12% | 47% | 83 | Key message: workload splits the team, an average of 2.9 would hide this. Note: team C (n=6) only reported together.

Fill in

What you type stays in this browser window. We store and send nothing.

SurveyWhat kind of survey?

ScaleWhich scale is used?

QuestionWhat do you want to know?

Your prompt

Help me analyse survey answers on an agreement scale.
Survey: [Survey]
Scale: [Scale]
Question: [Question]
Approach: 1. Check that every item uses the same scale direction and flag items that are worded in reverse. 2. Show the distribution for each item: share of each answer, number of answers and share without an answer. 3. Use the share of agreeing answers or the median as the main figure and explain why a plain average can hide a split. 4. Compare groups only when each group has enough answers and say where the numbers are too small. 5. Point out items where many chose the middle or did not answer and what that may mean. 6. Write three key messages without overstating the result.
Output: table per item with distribution and main figure, group comparison with notes, three key messages and open questions.

Take particular care to show distributions and never compare groups that are too small.

Before you answer, check: Are all instructions met? If key information is missing or a placeholder in square brackets is still in the text, ask instead of guessing. Mark assumptions as assumptions.

Help me analyse survey answers on an agreement scale.
Survey: [Survey]
Scale: [Scale]
Question: [Question]
Approach: 1. Check that every item uses the same scale direction and flag items that are worded in reverse. 2. Show the distribution for each item: share of each answer, number of answers and share without an answer. 3. Use the share of agreeing answers or the median as the main figure and explain why a plain average can hide a split. 4. Compare groups only when each group has enough answers and say where the numbers are too small. 5. Point out items where many chose the middle or did not answer and what that may mean. 6. Write three key messages without overstating the result.
Output: table per item with distribution and main figure, group comparison with notes, three key messages and open questions.

Take particular care to show distributions and never compare groups that are too small.

Before you answer, check: Are all instructions met? If key information is missing or a placeholder in square brackets is still in the text, ask instead of guessing. Mark assumptions as assumptions.

This is an instruction for an AI, not the result itself.

Where this prompt works

These AI tools are a good fit for this prompt:

How to use it

Fill in the fields or tap a suggestion. Leave out names, addresses and other personal data.
Copy the finished prompt into an AI tool of your choice.
Paste the answer counts per item or an export without names; group sizes help to judge comparisons.

Why does this work?

An average of 3.0 can mean that everyone is neutral or that half love it and half hate it. The distribution shows which one it is.

Tips

Report groups with very few answers only together, so that nobody can be identified.

You may use our prompts freely, including at work. Please do not republish them as your own collection. We give no warranty for AI results; check them yourself. Terms of use

Analyse agreement scale answers correctly

Result preview

Fill in

Your prompt

Where this prompt works

How to use it

Why does this work?

Tips

Also a good fit

Find cardinality explosions in metrics New

Estimate customer lifetime value simply New

Read a retention cohort table New