Executive summaries that turn a chart into a decision
The hardest part of an analysis is often the last mile: telling a non-technical stakeholder what the numbers mean and what to do about it, without burying the point. Turning findings into decision-ready writing is a top recurring AI use for analysts — as long as the model works only from the figures you verified and never invents a cause or a benchmark.
You are a data analyst who writes clear, decision-focused summaries for busy executives. Draft a summary of a finding. Audience and what they care about: {{audience}} The verified finding, with the exact numbers: {{finding}} The decision this informs: {{decision}} Caveats and known limitations of the data: {{caveats}} Structure it: - Bottom line up front — one sentence: what the data shows and the implication for the decision. - What the numbers say — the key figures I gave you, in plain language. - What it means — interpretation, clearly separated from the raw fact. - Recommendation or options — tied only to the decision above. - Caveats — the limitations I listed, stated plainly. Rules: - Use ONLY the figures I provided. Do not add a statistic, industry benchmark, trend, or dollar impact I did not give you. If a number would strengthen the point but I did not provide it, write "[FIGURE NEEDED]". - Never assert a cause. If the data is observational, say "associated with," not "caused by," and flag where an experiment would be needed to claim causation. - Keep it under 200 words, no jargon, no hedging filler. An executive should get the point in the first line.
Fill in your details and the prompt updates live — then copy.
Bottom line: Leads contacted within an hour convert more than twice as often as those contacted after a day (22% vs 9%), which supports investing in faster routing — with one caveat. What the numbers say: Across 4,100 Q2 leads, sub-1-hour contact converted at 22%; contact after 24 hours converted at 9%. What it means: Speed is strongly associated with conversion, but this is observational — faster-contacted leads may also be higher-intent to begin with. Recommendation: Fund a same-day routing pilot and measure it as a controlled test so we can attribute the lift, rather than assume it. Caveats: Not a randomized test; intent is a likely confounder.
The full workflow
- Lock down the exact figures and caveats from your analysis before you prompt
- Give the model only verified numbers and the decision at stake, no confidential identifiers
- Check every figure in the draft against your analysis, and fill any [FIGURE NEEDED] from the source
- Confirm the language distinguishes association from causation before it goes to a decision-maker
Watch out for
Models love to add a plausible cause or a round benchmark you never gave them. Every number and every causal claim in the summary is your professional representation — strip anything you did not verify.
Do not paste confidential business figures that identify your company (revenue, customer names, unreleased metrics) into a consumer tool. Coarsen the context and use an approved, training-disabled instance.
Watch the causation trap: an AI draft will happily write 'X drove Y' from observational data. If you cannot defend causation, the summary must not claim it.
Where this comes from
Every use case on this site is grounded in real reports from working data analysts — not invented by us.