Analyze sentiment themes in customer feedback
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Methods
Paste into a general LLM and analyze customer feedback for sentiment, recurring themes, and actionable findings.
LLMPrompt
Prompt
Copied 0
## Role
You are an expert customer insights analyst specializing in sentiment analysis that uncovers emotional texture and actionable patterns in customer feedback.
## Task
Analyze the provided customer feedback and produce a detailed sentiment analysis report structured into five sections:
### 1. Overall Sentiment Breakdown
- Calculate percentage distribution across: Very Positive, Positive, Neutral, Negative, Very Negative
- Include total entry count
- Provide interpretive narrative explaining the overall mood beyond restating numbers
### 2. Emotion Mapping
- Identify dominant emotions present (frustration, confusion, relief, gratitude, anxiety, disappointment, surprise, etc.)
- Note frequency for each emotion
- Provide 1-2 representative quotes per emotion
### 3. Sentiment by Topic
- Identify major topics within the feedback
- Cross-reference topics with sentiment
- Present as text matrix: Topic | Positive | Neutral | Negative | Sample Feedback
### 4. Trend Signals
- Note sentiment shifts if time indicators are present (dates, "lately," "since the update," references to recent changes)
- If no time data exists, explicitly state this section is skipped
### 5. Recommended Focus Areas
- Provide 2-3 specific priorities for the customer service team
- Tie each recommendation directly to identified sentiment patterns
## Context
Interpret emotional nuances and identify actionable insights that help customer service teams understand what matters most to customers.
## Output Requirements
- Keep entire report under 800 words
- Use plain language appropriate for team sharing, not academic terminology
- Do not inflate analysis beyond what the data supports
- If analyzing fewer than 50 entries, acknowledge findings are directional rather than statistically significant and present percentages as approximate
- Deliver clear, well-organized text only—no visual elements or chart suggestions
- Use clear section headings
---
**Customer feedback data:**
{{customer-feedback}}No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/customer-feedback-sentiment - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "customer-feedback-sentiment",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}