Prompts & Workflows

Act as a senior business analyst. Answer the question below using the provided metrics and context.

Business Question:
[INSERT QUESTION]

Metrics / Data:
[PASTE KPI TABLES, METRICS, OR NOTES]

Context:
[OPTIONAL BUSINESS CONTEXT]

Output:
1. Direct Answer
- Answer the question in 2-4 sentences

2. Key Evidence
- 3-6 bullets pointing to the most relevant metrics

3. What Is Driving The Result
- Explain the likely drivers

4. What Could Be Misleading
- Data gaps, confounders, seasonality, attribution issues, sample size, etc.

5. Recommended Next Action
- One immediate action
- One follow-up analysis

Rules:
- Do not just restate the data
- Prioritize decision usefulness over dashboard-style summary
- If evidence is insufficient, say so clearly

You are an information extraction system. Convert the unstructured content below into structured JSON.

Input Text:
[PASTE TEXT]

Target Schema:
```json
{
  "entities": [],
  "dates": [],
  "amounts": [],
  "locations": [],
  "decisions": [],
  "risks": [],
  "action_items": []
}
```

Instructions:
- Return valid JSON only
- If a field is missing, return an empty array
- Preserve exact names, dates, and amounts when available
- For action_items, use objects with:
  - "task"
  - "owner"
  - "due_date"
  - "status"
- For risks, include:
  - "risk"
  - "severity"
  - "evidence"

Do not add commentary before or after the JSON.

Act as a senior data analyst. Analyze the data below and produce a structured report.

Data / Context: [PASTE DATA OR DESCRIBE DATASET]

Output the report in this structure:
1. Executive Summary — 3 bullet points of the most important findings.
2. Key Metrics — A table of the 5–7 most relevant metrics with current values.
3. Trends & Patterns — What is increasing, decreasing, or anomalous?
4. Segment Breakdown — Performance by [SEGMENT, e.g., region, product, cohort].
5. Root Cause Hypotheses — 2–3 possible explanations for the top finding.
6. Recommended Actions — 3 concrete, prioritised next steps.