# Find the few causes behind most of my defects or complaints

A Pareto analysis of defect, complaint, or delay data that shows which few causes to fix first.

- Topic: Data & Analysis
- Framework: Few-Shot
- Level: Standard
- Tags: Analyze, Fill-in Template
- Source: https://www.thinkwithprompt.com/prompts/find-the-few-causes-behind-most-of-my-defects-or-complaints

## Prompt

```text
Run a Pareto analysis on my operational problem data.

**Data:** [PASTE - e.g. list of defects, complaint reasons, delay codes, downtime reasons, with counts or one row per event]
**Period covered:** [DATES]
**Cost or impact per category, if known:** [e.g. rework minutes, refund value]
**What I'm trying to improve:** [e.g. "reduce returns", "cut downtime"]

Steps:
1. Clean the categories: merge duplicates and near-duplicates (e.g. "late", "delayed", "LATE DELIVERY"), and list what you merged so I can check.
2. Build a table: category | count | % of total | cumulative %.
3. Do a second ranking by impact (cost or time) if I gave it - the most frequent problem isn't always the most expensive.
4. Identify the "vital few" that make up roughly 80% of the total, and say plainly if the data doesn't show a strong 80/20 pattern.
5. Flag data quality problems: vague categories like "other" or "misc" that are too large, missing values, or a short period that may not be representative.
6. For the top 3 categories, suggest likely root causes to investigate (as hypotheses, not conclusions) and what extra data would confirm them.

Describe the chart I should build (bars sorted descending plus cumulative line). Use only my numbers; don't estimate missing values.
```

## What to fill in

- DATES
- e.g. rework minutes, refund value
- e.g. "reduce returns", "cut downtime"

Free to copy and use. From ThinkWithPrompt (https://www.thinkwithprompt.com/), a library of 2,663 curated AI prompts.