Survey & Feedback Insight Extractor
Turn a pile of survey responses, NPS comments, support tickets, or review feedback into a structured insights report with themes, sentiment breakdown, priority actions, and quotable highlights. Works with any unstructured text feedback.
Pro tip
Dump in raw feedback — typos, shorthand, and all. AI handles messy data better than you think. The more responses, the more reliable the patterns.
How to use this prompt
- Pick your AI model. Choose the tab for Claude, ChatGPT, Gemini or Copilot — each variant is tuned for that model.
- Copy the full prompt. Click Copy Full Prompt to copy the text to your clipboard.
- Paste into your AI tool. Open your chosen model and paste the prompt into a new chat.
- Replace the
[placeholders]. Swap any bracketed fields for your company name, audience, product or tone. - Run and refine. Review the output. If anything is off, ask the AI to tighten tone, length or format.
Prompt Variants by Model
Claude
Claude 4.x
UPDATED APR 2026
You are a customer research analyst. I am going to give you raw feedback data from my customers. Analyze it and extract actionable insights.
<feedback_data>
[PASTE ALL FEEDBACK HERE — survey...You are a customer research analyst. I am going to give you raw feedback data from my customers. Analyze it and extract actionable insights.
<feedback_data>
[PASTE ALL FEEDBACK HERE — survey responses, NPS comments, reviews, support tickets, emails, whatever you have]
</feedback_data>
<context>
Feedback source: [NPS survey / customer support tickets / app store reviews / post-purchase survey / other]
Total responses: [NUMBER]
Time period: [e.g., "last 90 days"]
Business type: [YOUR_BUSINESS_TYPE]
</context>
Deliver:
1. **Theme analysis** — group all feedback into 5-8 recurring themes. For each: theme name, frequency (% of responses), sentiment (positive/negative/mixed), and 2-3 representative quotes.
2. **Sentiment breakdown** — overall positive/neutral/negative split with percentages.
3. **Top 5 action items** — ranked by impact × frequency. For each: what the feedback says, what to do about it, and expected impact.
4. **Hidden gems** — 2-3 insights that appear in only a few responses but signal an emerging trend or unmet need.
5. **Quotable highlights** — 5 best customer quotes usable for marketing, testimonials, or internal presentations.
Stay grounded in the actual data. Cite specific responses to support every finding.
Notes: Claude handles very large text dumps well inside XML tags — paste hundreds of responses. Ask for output in markdown table format for easy copy-paste into reports or slide decks.
ChatGPT
GPT-5
UPDATED APR 2026
Act as a customer research analyst. I have a batch of raw customer feedback and I need you to find the patterns and tell me what to do about them.
Feedback source: [NPS survey /...Act as a customer research analyst. I have a batch of raw customer feedback and I need you to find the patterns and tell me what to do about them.
Feedback source: [NPS survey / support tickets / reviews / post-purchase survey]
Number of responses: [NUMBER]
Time period: [e.g., "last 90 days"]
Business type: [YOUR_BUSINESS_TYPE]
Here is the raw feedback:
[PASTE ALL FEEDBACK]
Analyze this and give me:
1. Theme analysis — 5-8 recurring themes, each with: name, what % of responses mention it, sentiment, and 2-3 direct quotes.
2. Sentiment breakdown — % positive, neutral, negative.
3. Top 5 action items ranked by impact × frequency — what the feedback says and what I should do.
4. Hidden gems — 2-3 low-frequency insights that signal emerging trends.
5. Quotable highlights — 5 best customer quotes for marketing or internal use.
Base everything on the actual responses. No assumptions.
Notes: Upload a CSV through Code Interpreter for structured analysis with charts. ChatGPT can generate sentiment distribution graphs and word clouds automatically.
Gemini
Gemini 3 Pro
UPDATED APR 2026
I have a batch of customer feedback I need analyzed.
**Feedback source:** [NPS survey / support tickets / reviews / post-purchase survey]
**Responses:**...I have a batch of customer feedback I need analyzed.
**Feedback source:** [NPS survey / support tickets / reviews / post-purchase survey]
**Responses:** [NUMBER]
**Time period:** [e.g., "last 90 days"]
**Business type:** [YOUR_BUSINESS_TYPE]
Here is the raw feedback:
[PASTE FEEDBACK]
Analyze it and deliver:
1. Theme analysis — 5-8 themes with frequency %, sentiment, and 2-3 quotes each
2. Sentiment breakdown — positive/neutral/negative percentages
3. Top 5 prioritized action items (impact × frequency)
4. Hidden gems — 2-3 low-frequency signals worth watching
5. Quotable highlights — 5 best quotes for marketing or presentations
Research whether the themes you find align with common complaints in my industry. Compare my sentiment distribution to industry averages if available.
Notes: Gemini can benchmark your feedback themes against real-time industry complaint data via search grounding. Share a Google Forms response sheet directly for seamless ingestion.
Copilot
Copilot (Microsoft 365)
UPDATED APR 2026
I have customer feedback that needs analyzing.
Source: [NPS survey / support tickets / reviews / post-purchase...I have customer feedback that needs analyzing.
Source: [NPS survey / support tickets / reviews / post-purchase survey]
Number of responses: [NUMBER]
Time period: [last 90 days / other]
Business type: [YOUR_BUSINESS_TYPE]
Feedback:
[PASTE ALL FEEDBACK]
Analyze it and give me:
1. 5-8 recurring themes — name, frequency %, sentiment, and 2-3 quotes each
2. Overall sentiment split — % positive, neutral, negative
3. Top 5 action items ranked by impact × frequency
4. 2-3 hidden gems — low-frequency signals worth watching
5. 5 best customer quotes usable for marketing
Base everything on the actual feedback, not assumptions.
Notes: Copilot in Excel can process feedback data with pivot tables and sentiment tagging. Paste responses into a column, then ask Copilot to categorize and chart them — it generates the analysis in-sheet.
Frequently Asked Questions
What does the Survey & Feedback Insight Extractor prompt do?
Turn a pile of survey responses, NPS comments, support tickets, or review feedback into a structured insights report with themes, sentiment breakdown, priority actions, and quotable highlights. Works with any unstructured text feedback.
Which AI models is this prompt tested on?
This prompt is field-tested on Claude, ChatGPT, Gemini and Copilot. Each model has its own optimized variant above.
Do I need a paid AI account to use this prompt?
No. This prompt is written to run on the free tier of Claude, ChatGPT, Gemini and Copilot. Paid tiers simply give you longer context windows and faster responses.
Can I customize this prompt for my business?
Yes. Any text inside square brackets is a placeholder you replace with your own business details, such as company name, audience, product or tone. You can also ask the AI to adjust format, length or style after the first output.
When was this prompt last verified?
Each model variant above shows its own freshness stamp. AlignAI re-verifies every prompt at least monthly and rebuilds when a major model changes.
Don’t see what you need? tailored to your use case.