Prompt catalog
Browse reusable AI prompts by topic, then open any prompt to copy and adapt it for your workflow.
375 prompts · page 6 of 42
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
Scans a full interview transcript for everything one participant said about a single named topic, quoting directly wherever possible instead of paraphrasing, and flags any conflicting or nuanced responses on that topic. Useful for building a topic-by-topic view across multiple transcripts before formal coding begins, rather than reading full summaries each time.
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.
Describe your DataFrame's columns and sample rows, list up to four charts you need, and specify a color palette, figure size, and where the charts will be viewed — slides, web, or print. The prompt returns complete, runnable matplotlib and seaborn code for all four charts at once, each with a descriptive title, labeled axes with units, a legend only when needed, and annotations calling out key data points, without unnecessary chartjunk.
Paste a raw interview transcript to get a first-pass inductive code list before any themes are decided. - Builds a granular code list rather than pre-collapsed themes - Each code gets a short 2-5 word label - Each code gets a one-sentence definition - Each code is paired with a direct illustrative quote from the transcript
Paste in the flat code list from an earlier coding pass and this prompt organizes it into 3-6 coherent themes for a qualitative results write-up. Each theme gets a descriptive name that makes an analytical claim rather than just labeling a topic, a list of the component codes that belong to it, and a 2-3 sentence description of what the theme actually argues, while pushing back on single-code themes unless there's a strong reason for one.
List the columns with missing data — name, type, approximate percent missing, and likely cause — and this prompt classifies each one as MCAR, MAR, or MNAR before recommending a fix. It weighs whether the missingness itself is informative, considers adding a was_missing flag, justifies the chosen imputation method against alternatives for every column, and outputs the Python code implementing the strategy column by column.
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
Give the numeric columns to check and describe what the dataset represents, and this prompt detects outliers with IQR, Z-score, and isolation forest in parallel, then classifies each one as a data-entry error, a genuine extreme value, or part of a systemic cluster pointing to an upstream process bug. It shows each outlier alongside its row context, quantifies how much removing them shifts the mean and median, and generates Python code that flags the outliers and outputs a cleaned dataset with the recommended handling applied.