Tag
Raw numbers don't explain themselves. These prompts help you turn a dataset into patterns, patterns into findings, and findings into a summary someone outside the spreadsheet can actually use.
22 prompts · page 2 of 3
Specifies an interactive exploration tool for a dataset's dimensions and metrics, covering layout, filter and drill-down behavior between named levels, comparison views, hover details, transitions, and the default view a user sees before touching anything. Adds a tool-specific implementation plan and performance notes for the expected row count, plus working Plotly Dash or Streamlit prototype code when the target tool is Python-based.
Writes up a spike, drop, or unusual pattern the way an analyst should, starting from the anomaly description, time range, affected metrics, magnitude, and supporting data. States what happened in one sentence, quantifies the business impact beyond a percentage change, presents likely causes with evidence, rules out false positives like seasonality or pipeline bugs, and recommends both immediate action and prevention — tailored to a chosen audience and tone.
Examines how key metrics actually moved over a date range and granularity before anyone tries to forecast them. Covers overall trend direction, seasonality at weekly through annual scales, anomalies or change points, day-of-week patterns, and year-over-year growth rates, reporting the time window and magnitude behind every finding so it feeds directly into an anomaly report or forecast.
A general-purpose starting point for pulling business-relevant takeaways out of almost any dataset, given its context and key metrics. - Covers: key trends, anomalies or outliers, correlations between variables, and segment performance - Produces: actionable recommendations, risks or warnings, and next steps - Framed around business impact rather than raw statistics - Good default when it's unclear which specialized analysis prompt fits better
Feed in a target variable, its type, a list of candidate predictor columns, and the dataset's row and column counts, and get back a rigorous drivers-of-X analysis instead of a hand-wavy guess. The prompt runs univariate correlation, mutual information, tree-based feature importance, and permutation importance side by side, explains why the four rankings disagree, flags features that are likely proxies for the same underlying driver, and closes with a plain-language summary naming the top three drivers and what they mean for the business.
Paste raw dashboard numbers plus business context, the time period, stated goals, and the prior period's figures to get a narrative read ready for a metrics review meeting. - Performance summary against goals and the previous period - Positive trends and concerning trends called out separately - Progress toward each stated goal and the likely drivers behind changes - Recommended actions and a forecast for the next period
Paste in user or customer data, define how cohorts should be grouped, pick a metric to track — retention, revenue, or engagement — and set the time period, for a lighter-weight cohort read than a full retention-table build. Covers cohort performance comparison, retention curves, revenue trends by cohort, behavioral patterns, drop-off points, and the factors separating strong cohorts from struggling ones, plus improvement opportunities.
Specify the entity type being cohorted, how cohorts are defined (signup month, hire date, etc.), the key metric to track, the time granularity, and the relevant dataset columns, and this prompt builds a full cohort by time period retention or engagement table from raw data. It flags which cohorts meaningfully beat or lag the average, checks whether newer cohorts trend better or worse over time, runs a time-to-event calculation like time to 50% churn, and delivers the Python or SQL code that generates the whole analysis plus a heatmap.
Paste in column names, types, and roughly 20 sample rows along with the role you're framing findings for — a product manager, a CFO — and this ready-made EDA prompt returns summary statistics for every numeric column, value counts for categorical columns, a missing-value breakdown, distribution shapes for key variables, the five most interesting anomalies, and ten business-relevant questions the data could answer, ranked by value. A solid default first pass on any dataset you haven't explored yet.