253 AI Prompts for Data Analysis

## Role
You are an expert data analyst specializing in education metrics, with deep knowledge of institutional performance measurement and sector-wide benchmarking standards.

## Task
Analyze educational data to identify improvement opportunities and create a comprehensive performance report comparing key metrics against industry benchmarks.

## Context
{{institutional-context}}

Work systematically through:
1. Review and organize the provided data
2. Identify key performance metrics relevant to the focus area
3. Research and compile industry benchmarks for those metrics
4. Analyze current performance against standards
5. Identify significant gaps and improvement opportunities
6. Synthesize findings into an actionable report

## Output
Deliver your analysis as:

**Performance Analysis Table** (markdown format with 4 columns):
- Metric
- Current Performance  
- Industry Benchmark
- Gap An

You are a senior analytics engineer specializing in event-driven conversion funnels and user journey analysis.

Write a SQL query that calculates a **sequential, ordered multi-step conversion funnel** from an events table. The query must:

- **Enforce step order per user**: count only the first occurrence of each step in sequence; a user must complete step N before step N+1 is recognized
- **Apply an attribution window**: events must fall within {{attribution-window}} of the user's first step to count toward the funnel
- **Handle edge cases**: users who repeat steps (count only the first), skip steps (do not credit them for later steps), or never complete the funnel
- **Calculate and return**:
  1. Count of unique users reaching each step
  2. Drop-off count and drop-off % between consecutive steps
  3. Overall conversion rate from first step to final step

**Context:**
{{funnel-definiti

You are a SQL analyst specializing in window functions for analytical queries.

Write a SQL query that answers the following business question using the appropriate window function:

{{business-question}}

Table schema:
{{schema}}

# Requirements

1. **Choose the correct window function** from ROW_NUMBER(), RANK(), DENSE_RANK(), LAG(), LEAD(), or aggregate window functions (SUM/AVG/COUNT OVER). Explain in one sentence why you chose it over alternatives.

2. **PARTITION BY**: Write one line explaining your partitioning logic and what each partition represents.

3. **ORDER BY**: Write one line explaining your ordering choice and how it affects the window calculation.

4. **Edge cases**: Identify one specific scenario where ties, NULLs, or missing periods would change the result, and state how your query handles it.

5. **Worked example**: Provide a small sample dataset (4-6 rows) and show 

You are an expert SQL analyst writing production-grade revenue reports.

Write a SQL query that produces a revenue report from `orders` and `customers` tables with the following requirements:

**Schema context**
{{schema-details}}

**Report specification**
- Group by: {{grouping}}
- Metrics: total revenue, order count, average order value, unique customer count
- Explicitly handle refunds and cancelled orders (state your treatment: exclude, include as negative, or separate column)
- Clearly state whether tax and shipping are included in revenue and document your decision in a comment
- Use consistent date-boundary logic: periods must not overlap and must not leave gaps (e.g., month boundaries at midnight on the 1st, week start on Monday 00:00:00)

**Output the query with:**
1. Opening comment block documenting:
   - Revenue definition (what is included/excluded)
   - Refund and cancellat