YES

As of 13 August 2026, AI can calculate your Net Promoter Score.

Most people should do this themselves; the prompt is on this page.

Can you do it?

5 minutesto a draft.

15 minutesto something you’d act on.

Cost, all in£0

Skill needednone

Who has to check ityou

What the alternative costsThe available tool data does not provide a comparable price for a specialist NPS calculation service.

If this goes wrong: you publish an incorrect customer metric or make a poor comparison, but you can recalculate it from the original responses.

What to actually do

  1. Do it yourself

    The route this page recommends

    A chat interface, no skill needed, and roughly 15 minutes until you can act on the result.

    How to actually do it

    1. Open a spreadsheet or your chatbot and gather the original 0 to 10 answers for the survey period, without names or other unnecessary personal data.
    2. Paste the responses into the prompt, along with the survey dates and the exact question asked.
    3. Ask the model to validate every entry, count detractors, passives and promoters, and show the percentages and formula.
    4. Compare the model's total response count with the number of completed survey answers in your survey platform.
    5. Recalculate the promoter and detractor percentages from the counts, apply percentage of promoters minus percentage of detractors, and check the rounding.
    6. Save the verified score with the survey period, response count and classification counts before sharing it with your team.

    Prompt

    Calculate the Net Promoter Score from the survey data below. Treat responses from 0 to 6 as detractors, 7 to 8 as passives, and 9 to 10 as promoters. First check that every response is a whole number from 0 to 10 and identify any missing, duplicated or invalid entries. Then show: total valid responses, number and percentage of detractors, passives and promoters, the formula used, and the final NPS rounded to the nearest whole number. Use NPS = percentage of promoters minus percentage of detractors. Do not include passives in the subtraction. Show enough arithmetic for me to verify it, and do not infer or replace missing data. Survey period: [START DATE to END DATE]. Survey question: [QUESTION]. Responses: [PASTE RAW 0 TO 10 RESPONSES HERE].

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

  2. Use a tool built for this

    Second choice

  3. Hand it to a person

    The distant third

    A person who owns the outcome does this end to end, worth it when the failure is dear.

What it gets wrong

Even on a YES, the friction has a name: judgement under ambiguity and stakes of error.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs2
Verification2
Liability2
Effort delta2
Total10 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT calculate my NPS?
Yes. Give it the valid 0 to 10 responses, ask it to show the counts and arithmetic, and check those figures against your survey platform.
What is the formula for Net Promoter Score?
Classify scores from 0 to 6 as detractors, 7 to 8 as passives, and 9 to 10 as promoters. NPS is the percentage of promoters minus the percentage of detractors, with passives excluded from the subtraction.
Can AI calculate NPS from a spreadsheet?
Yes, if you upload or paste the relevant response column and tell it which entries to treat as valid. Keep a copy of the original data and check the model's total against the spreadsheet before using the result.
Can AI tell me if my NPS is good?
It can compare the score with benchmarks or your own history if you provide reliable context, but the number alone does not explain customer sentiment. You still need to examine the survey question, response mix, customer segments and reasons for the scores.

Nearby answers

All Feedback & NPS analysis rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.