I have a pile of NPS / customer feedback comments. Help me synthesize them into a small set of insights I can actually act on.
COMMENT VOLUME: {how_many}
COMMENT FORMAT (what fields you have): {nps_score / comment / role / segment / etc.}
WHO ASKED FOR THIS ANALYSIS: {leadership / your_team / a_customer_meeting}
WHAT THE BUSINESS IS WORRIED ABOUT: {dropping_nps / specific_segment / specific_feature}
TIME I HAVE: {hours_or_days}
WHAT I'D DO WITH THE OUTPUT: {update_roadmap / write_a_doc / kill_a_feature / change_pricing}
DESIGN A METHOD:
1. **Tagging schema** — 5-10 themes I can tag comments under (e.g. 'product gap', 'pricing', 'CS responsiveness', 'reliability', 'specific feature request'). Hierarchical if needed.
2. **The 80/20 read** — which themes do I focus on first to capture most of the signal.
3. **The 'detractor vs promoter' split** — what are detractors saying that promoters aren't, and vice versa.
4. **The 'verbatim moment' — one comment per theme** that captures it best. (Specific quotes carry more weight than synthesis.)
5. **A leadership-ready summary** (1 page) — what we heard, what we should do, what we should NOT do.
6. **A roadmap impact note** — which existing roadmap items get re-prioritized, which get killed, which get added.
7. **A 'check this again in 90 days' plan** — what comments to look for next time to know things changed.
No 'we love our customers'. Calm, evidence-based, specific.0 copies·0 saves·4 views
229 words·1,435 chars
Sample output
Volume: 320 NPS comments from last 6 months. Fields: score (0-10), comment, segment (SMB/mid/enterprise), CSM name. Asked by: leadership for end-of-quarter readout. Business worry: NPS dropped from 42 to 28 last quarter. Time: 1 day. Use: rebalance Q3 roadmap.
1. Tagging schema (top 8):
Tag every comment with 1 PRIMARY theme + 1 OPTIONAL secondary. Don't over-tag.
Keep it to ≤ 8 buckets. More buckets = scattered signal that doesn't drive prioritization.
Parameters
Text generation parameters
FAQ
Tag comments alone in a quiet room. Synthesis is what's worth talking about — tagging is heads-down work. Doing it in a meeting wastes 80% of the time on small disagreements. The prompt targets ChatGPT (GPT-4) and lives in the Analysis & Research category on mycopyprompt.
This prompt is written for ChatGPT (GPT-4). It's a text/chat prompt — paste it into ChatGPT (GPT-4) (or compatible LLMs like Claude or GPT-4) to get the expected output.
1. Click the Copy button on this page to copy the full prompt. 2. Open ChatGPT (GPT-4). 3. Paste the prompt into a new conversation. 4. Replace any {placeholders} with your specifics, then send. Most prompts produce the right output on the first try; complex ones may need 1-2 iterations.
Yes — every prompt on mycopyprompt is free forever. No paywall, no signup wall for browsing or copying. You can use it for personal or commercial work, just don't redistribute the entire mycopyprompt library.
Absolutely — most prompts are templates. Look for {placeholders} (curly braces) and swap them with your own values. You can also reword sections, add constraints, or chain it with other prompts.
See the "Sample output" panel above — that's a real example of what ChatGPT (GPT-4) returns when this prompt runs. Your output will vary in wording but should follow the same structure and depth.
Similar prompts
Matched against every prompt in the catalog by title.
2. The 80/20 read:
Of 320 comments, expect ~60% to fall into 2-3 themes. Find those 2-3, then write the rest of the analysis around them.
Example distribution after a quick pass:
Focus the leadership doc on the top 3. Mention the others in an appendix.
3. Detractor vs promoter split:
Filter detractors (0-6) and promoters (9-10) separately.
Detractors most common themes:
Promoters most common themes:
Key insight: the same theme (CS) is the #1 promoter AND the #2 detractor. That's not contradiction — that's variance. Some CSMs are great; some aren't. The fix isn't 'change CS strategy'; it's 'figure out which CSMs and why'.
Key insight: promoters' feature gap comments are RECOMMENDATIONS. Detractors' feature gap comments are EXISTENTIAL. Different urgency.
4. Verbatim moments (one per top theme):
Reliability: 'In Q2 we had 3 outages of 20+ minutes during business hours. Our finance team can't run reports during outages. I love the product but I can't keep defending the reliability to my CFO.' — VP Finance, mid-market
Specific feature gap: 'We've been waiting 14 months for the SOC2-compliance export feature. It's on the public roadmap. Either ship it or take it off the roadmap so we can stop telling our compliance team it's coming.' — Director of Security, enterprise
CS responsiveness: 'Our CSM [name] responds within 2 hours on average. She's the reason we expanded last quarter. Whatever you're paying her, double it. The previous CSM took 5-7 days to reply, which is what made me give a 6 in Q3.' — VP Operations, mid-market
5. Leadership summary (1 page):
NPS quarterly readout — what 320 customers told us
The drop from 42 to 28 is driven primarily by 3 specific things, in this order:
1. Reliability (31% of detractor comments). Three outages > 20 min in Q2 hit mid-market and enterprise particularly hard. This is now their #1 reason for the lower score.
2. CS quality variance (28% of detractor comments). Customers who give a 9+ overwhelmingly cite a great CSM. Customers who give a 6- often cite slow / unresponsive CS. This is the SAME team — the variance, not the average, is the problem.
3. Existing roadmap items shipping later than expected (15% of detractor comments). Customers tracking the public roadmap are visibly losing patience on SOC2-compliance export (14 months) and the SAML upgrade (9 months).
What I recommend we do this quarter:
What I recommend we do NOT do:
6. Roadmap impact:
Re-prioritized UP (this quarter):
Re-prioritized DOWN:
Added:
7. 90-day re-check:
When we re-sample NPS at end of Q3, expect to see:
If reliability mentions DON'T drop, the engineering investment isn't being felt by users. Investigate.