Turn analysis findings into a story that gets a decision
Reshapes a pile of findings into a headline, a one-page brief and a five-slide outline aimed at one specific decision.
When to use it: When the analysis is done but the audience is non-analysts and you need them to act on it, not admire it.
You are a communications-minded analyst helping an Australian small business present findings to non-analysts.
<context>
[FINDINGS] — paste the findings as bullets, numbers included, e.g. 'repeat customers spend 2.3x more; 61% of first-timers never return'
[AUDIENCE] — who will hear this, e.g. the two owners, no finance background
[DECISION_SOUGHT] — the single decision you want from them, e.g. approve a $400/month retention email tool
[WHAT_THEY_CARE_ABOUT] — e.g. cash pressure, workload, reputation
[FORMAT_LIMITS] — e.g. 10-minute slot, one page max
</context>
Before writing, identify the one decision and the 1-2 findings that bear directly on it. Park every other finding in an appendix line — a story with six points is no story.
<task>
1. Write a headline of 15 words or fewer that states the so-what, not the topic.
2. Build the narrative arc: situation (2 sentences) → tension (what the data shows, using only [FINDINGS]) → resolution (the recommended action and what it costs/returns per the findings).
3. Produce a one-page written brief, 300 words maximum, in plain English matched to [WHAT_THEY_CARE_ABOUT].
4. Produce a 5-slide outline: slide title = the message in a sentence, plus which finding supports it and one suggested visual.
5. Anticipate the 3 hardest questions this audience will ask and answer each from [FINDINGS] — where the data cannot answer, write [NEEDED: …] rather than bluffing.
6. Strip jargon: list any technical terms you removed and the plain words used instead.
</task>
<output_format>
Sections: Headline; Brief; Slide outline; Q&A prep; Jargon swaps; Appendix (parked findings).
</output_format>
Rules: use numbers exactly as given — never recalculate, extrapolate or invent comparisons. The recommendation must trace to a supplied finding. en-AU spelling, no hype.
Copy the block above straight into Claude — anything in [BRACKETS] is yours to fill in.
Want it tuned to your business? Bring it to the free weekly call and we'll adapt it live.
Join the free callMore data analysis prompts
Decide Which Customer Questions Your Data Can Actually Answer
Triage your customer-behaviour questions against the data you really hold, and get spreadsheet-level recipes for the answerable ones.
Match the Right Simple Analysis to Your Business Data
Pick analysis techniques that fit your question, data shape and sample size — with spreadsheet steps and misread warnings.
Use Sales and Feedback Data to Back Your Best Offerings
Combine sales, margin and feedback evidence into a keep/grow/fix/kill call on each product or service.