Pick the three insights and five numbers my executives need
Ranks your findings down to the single most important insight, the top three, the five numbers to watch, and the biggest surprise.
The prompt
Help me decide what my executives actually need to know from this data.
Data or analysis: [PASTE]
Executive audience: [e.g. "CEO and CFO", "regional leadership team"]
What they are deciding or worried about right now: [e.g. "whether to expand the pilot", "margin pressure"]
Targets or goals this relates to: [OPTIONAL - budget, OKRs, benchmarks]
Rank candidate insights with these tests:
- Materiality: how big is the effect in money, customers, or risk?
- Decision relevance: would it change what leaders do?
- Novelty: is it new to them, or something they already know?
- Confidence: how solid is the evidence?
Return:
1. The one insight that matters most, in one sentence, with why it beats the others.
2. The three insights an executive needs, each with: a headline sentence, the supporting number, the so-what, and a suggested action or question.
3. The five numbers to watch: Metric | Current value | Comparison (prior period, target, or benchmark) | Why it matters | What level should trigger concern.
4. The most surprising pattern in the data, whether it looks like a real signal or a data artifact, and a quick check to confirm.
5. What I left out and why: findings that are true but not executive-level.
Use only figures from my data; mark anything missing as [ADD DATA]. Keep the caveat on any low-confidence insight instead of dropping it.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- PASTE
- e.g. "CEO and CFO", "regional leadership team"
- e.g. "whether to expand the pilot", "margin pressure"
- OPTIONAL - budget, OKRs, benchmarks
- ADD DATA
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Break down why a number changed between two periodsA driver breakdown and bridge that shows exactly which segments, volume, price, or mix effects caused a metric to move.
- Check whether my data shows causation or just correlationSeparates trend, correlation, and possible causation in your analysis and gives you the strongest claim you can honestly make.
- Turn my analysis findings into a clear recommendationConverts findings into options, a recommended choice, trade-offs, assumptions, and success metrics a decision-maker can act on.