Read customer satisfaction scores correctly

Prompt that analyses satisfaction scores with count, distribution and comments instead of showing a single number. Paste it into an AI tool of your choice, which then puts the satisfaction scores in context.

Topic: Spreadsheets & data
Type: Prompt
Level: Intermediate
Time: about 10 min

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

Result preview

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

| Quarter | Score | Responses | rough range | | Q2 | 42 | 118 | 30 to 54 | | Q3 | 31 | 64 | 14 to 48 | Distribution Q3: 26 promoters, 25 passives, 13 detractors Themes at 0 to 6: delivery time (8), follow-up questions in support (5) Themes at 9 to 10: advice (14) Answer: with 64 responses the drop is not certain. Delivery time, however, appears newly and often among detractors. Open: responses came almost only by email after an order

Fill in

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

MetricWhich score?

DataWhat data is available?

QuestionWhat do you want to know?

Your prompt

Analyse the following satisfaction data.
Score and scale: [Metric]
Data: [Data]
Question: [Question]
Approach: 1. Check how many responses there are per period and group, and say from what point a change can be more than chance. 2. Calculate the score and show the distribution of answers, not only the average. 3. Compare periods or groups with a rough uncertainty range. 4. Sort the free-text comments into themes and count how often each theme appears with low and with high ratings. 5. Say who probably did not respond and how that can distort the picture. 6. Answer the question in three sentences.
Output: a short table with score, count and range, a theme list, the answer and open points. Do not invent figures.

Take particular care to always check the number of responses first and never present fluctuations as a trend.

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.

Analyse the following satisfaction data.
Score and scale: [Metric]
Data: [Data]
Question: [Question]
Approach: 1. Check how many responses there are per period and group, and say from what point a change can be more than chance. 2. Calculate the score and show the distribution of answers, not only the average. 3. Compare periods or groups with a rough uncertainty range. 4. Sort the free-text comments into themes and count how often each theme appears with low and with high ratings. 5. Say who probably did not respond and how that can distort the picture. 6. Answer the question in three sentences.
Output: a short table with score, count and range, a theme list, the answer and open points. Do not invent figures.

Take particular care to always check the number of responses first and never present fluctuations as a trend.

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.
Calculate the score once with and once without the last ten responses. If it jumps a lot, the sample is too small for a firm statement.

Why does this work?

With a few dozen responses, a recommendation score easily swings by many points. Only the count, the distribution and the comments show whether something has really changed.

Tips

Remove names, email addresses and customer numbers from the comments before you paste them in.

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

Read customer satisfaction scores 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