# Customer Feedback Clusterer Runbook

## Project Context To Prepare
- Project goal
- Current repository or workflow context
- Current context
- Goal
- Audience or stakeholder
- Constraints
- Available notes or data

## Input Template
Project:

Goal:

Current context:

Constraints:

Available files, notes, or data:

Expected output:
- feedback synthesis
- Themes with counts
- Representative quotes
- Recommended actions

## Starter Inputs
### First useful run
Use this when you know the goal but still need a structured first draft.

Cluster 100 support notes into product improvement themes.

Context:
- Current state:
- Constraints:
- Audience:
- Success criteria:

### Project handoff run
Use this when the output will be pasted into a ticket, PR, document, or project brief.

Goal: produce feedback synthesis for a real project.
Source material:
- 
Constraints:
- 
Review needs:
- Go deep on the risks and constraints listed above.
- Mark assumptions.
- Flag missing context.

### Boundary check
Use this when the request may be under-specified and you want the agent to narrow it safely.

Prioritize roadmap changes from three anecdotal comments.

Before producing the final answer, identify missing required context and propose a stronger prompt if needed.

## Setup Context Notes
- Prepare raw feedback, source channels, customer identifiers, date range, and known duplicates.
- Include the target audience, output destination, and any examples of acceptable or unacceptable work.
- Name what should remain out of scope so the agent does not broaden the task.

## Good Input Example
CS 채널에 쌓인 고객 의견 100개를 제품 개선 항목으로 정리하는 상황

Goal: produce feedback synthesis for a real project.
Constraints: keep the result specific, structured, and ready for handoff.

## Weak Input Example
Help me with Customer Feedback Clusterer.

## Weak Input Diagnostics
### Help me with Customer Feedback Clusterer.
- Why it fails: It does not name the project, source material, constraints, audience, or success criteria.
- Stronger input: Cluster 100 support notes into product improvement themes. Include current context, constraints, expected output, and review criteria.

### Make this better.
- Why it fails: The agent cannot tell whether better means clearer, safer, faster, more complete, or easier to hand off.
- Stronger input: Improve the output for CS 채널에 쌓인 고객 의견 100개를 제품 개선 항목으로 정리하는 상황. Optimize for feedback synthesis, keep assumptions explicit, and list the changes made.

## Expected Output Shape
- Themes ordered by impact on the stated goal: name, count and item numbers, verbatim quotes, severity with the reason, and likely cause
- A recommended action per theme with owner and success signal, sized to the stated capacity
- Items that fit no theme and one-off requests
- Unsupported ideas kept to one line each under "Also worth watching"

## Output Checklist
- Counts are exact and add up to the total
- Quotes are verbatim
- Every piece of context given (releases, churn reasons, capacity) is tied to the themes it explains
- Inferences are marked [ASSUMPTION]
- No feedback, counts, or quotes are invented

## Failure Modes
- Theme counts do not add up to the number of items
- Quotes are paraphrased or invented
- Actions ignore the capacity or goal the user gave
- Counts are inflated to support a conclusion the data does not show

## Handoff Tips
- Paste relevant project files, notes, or constraints before asking for the final output.
- Ask for a first draft, then request a stricter revision using the checklist.
- Keep the generated output with the project ticket, PR, proposal, or team document.