Prompt Cookbook

What data do I have access to here, and what are 5 good questions I could ask it?

Describe the [orders] table in business terms: what's a row, what are the key fields, how fresh is it?

What was [metric] [last week / last month / this quarter]? Compare to the previous period and tell me if the change is meaningful or noise.

Top 10 [customers / products / pages] by [metric] this [period], with each one's share of the total.

[Metric] by [day/week/month] for the last [N] [periods], as a chart, with a trend line.

Explain exactly how you calculated that: source table, filters, time window, definition. What assumptions did you make?

Give me a methodology footnote for that answer: source, window, filters, governed vs ad hoc, data freshness.

I expected [value] based on [reference report]. Why might your number differ?

Segment [metric] by [dimension]. Which segments drive the total, which are growing or shrinking fastest?

[Metric] moved from [A] to [B] between [period 1] and [period 2]. Decompose the change by [dimension] and rank the contributors.

Compare [segment A] vs [segment B] on [metrics]. Where are they most different, and is the difference statistically meaningful?

Plot [metric] weekly for the past year. Flag anomalies and tell me if the trend is changing after seasonality.

Did anything unusual happen in our data [yesterday / last week]? Check the main metrics and flag outliers.

Project [metric] through [horizon] with uncertainty bands. State the assumptions and what would break them.

Make that a [bar / line / stacked area / scatter] chart. Show top [N] only, group the rest as "Other," sort descending.

Add a target line at [value] and annotate the months we missed it.

Turn this thread into an executive report: summary up top, charts with takeaways, methodology appendix. PDF please.

Build a dashboard with [chart 1], [chart 2], and [table], with filters for [date range] and [dimension].

Export that table as CSV.

Create a playbook "[name]" that runs [every Monday 9am]: [contents]. Email it to [me / list] and post to [#channel].

Create a feed agent that watches [domain] daily and posts only when something genuinely changes. Build on prior findings.

Remind me [when] to [do thing].

Our official definition of [metric] is [definition]. Save it to the ontology (propose the patch).

Vocabulary: "[term]" means [meaning]. Save to the ontology.

Remember my preferences: [concise answers / timezone / default windows / what "my accounts" means].

That number looks off. Walk me through the calculation step by step, and list everything that was excluded.

Recalculate using [other definition] and show both side by side.

What data would we need to answer this properly?