Calculate Net Promoter Score from survey data
Sort raw 0-10 feedback scores into standard groups and compute your Net Promoter Score with clear segment breakdowns.
Data analysis prompts for making sense of spreadsheets, survey results, dashboards and metrics: plain-English summaries, trend checks, chart choices and follow-up questions to verify.
For ChatGPT, Claude and Gemini · Updated
58 prompts · page 2 of 3
Sort raw 0-10 feedback scores into standard groups and compute your Net Promoter Score with clear segment breakdowns.
Turn raw subscription tables into clear tier-by-tier health comparisons. Identify which pricing plans drive revenue expansion, retention, or churn risk.
Determine whether a monthly revenue or traffic drop is normal seasonality or an operational problem. Use this during monthly business reviews.
Quickly understand the purpose, column types, and data quality risks of a messy raw CSV export. Ideal when inheriting unfamiliar operations sheets.
Generate a practical exploratory data analysis plan when starting with unfamiliar data. Frame key business questions, data hygiene checks, and visualization priorities.
Translate complex balance sheets and quarterly income reports into plain English. Quickly spot shifts in revenue, margins, and operational spending.
Turn complex chart summaries or data points into clear, executive-ready captions. Use it before sending reporting decks to busy stakeholders.
Calculate cell-weighting factors and adjust skewed survey metrics to reflect true population demographic benchmarks.
Turn regression coefficients, p-values, and confidence intervals into direct business trade-offs. Use this when presenting analytical models to non-technical executives.
Break down broad survey scores into department-level trends to spot localized burnout and turnover risks.
Surface filtering tricks, omitted baselines, and date cutoffs hiding behind pasted dashboard metrics. Use this before presenting figures to executive leadership.
Stress-test observed metric correlations to identify hidden confounding variables and avoid false conclusions.
Challenge data findings and business recommendations before presenting them. Use this to catch false correlations, survivorship bias, and hidden assumptions.
Map repetitive back-and-forth navigation and error loops within onboarding flows. Use this to pinpoint confusing validation rules and navigation traps.
Identify whether null values represent expected business logic or export dropouts. Use it when auditing schema quality or preparing datasets for modeling.
Uncover hidden conversion bottlenecks across mobile, desktop, and paid channels. Use this when top-line conversion dips but sitewide funnels show no obvious break.
Design a clean scorecard structure with clear metric definitions, target thresholds, and operational owners. Perfect for structuring monthly business reviews.
Find out if your survey response count is reliable enough to make business decisions or if the margin of error is too wide.
Spot budget leakages and hidden scope creep by auditing estimated versus actual hours. Use it during mid-project reviews or client budget checks.
Normalize sales performance by factoring in territory quality, lead volume, and deal size. Use when conducting fair sales performance appraisals.
Spot deceptive 4 and 5-star reviews that contain serious product bugs, billing complaints, or hidden cancellation risks.
Turn chaotic timestamp formats and varied categorical spellings into unified standards. Use it when mismatched export values break dashboards.
Analyze past forecast misses to identify systematic over- or under-projection patterns. Use this before locking in next quarter's revenue or operational targets.
Match disparate, poorly named export headers to a structured target data schema. Use it when consolidating CSV reports from multiple platforms.
FAQ
Most people staring at an exported spreadsheet or survey table do not need complex code first; they need to know what moved, what looks unusual and which cut of the data is worth checking next. These prompts take pasted tables, summary figures or open-ended survey responses and organize them into clear findings, caveats and recommended visuals.
Every prompt runs as pasted in ChatGPT, Claude or Gemini without requiring placeholders or setup. Each one includes a realistic example output so you can check the structure before pasting your own numbers, and asks the assistant to flag missing context or small sample sizes instead of overstating a conclusion.
Paste a clean summary table, a representative slice of rows with clear column headers or aggregated totals rather than a massive raw export. Removing personal identifiers such as customer emails or account numbers protects privacy while still giving the assistant enough structure to spot trends, outliers and useful follow-up checks.
Yes. Qualitative coding is one of the strongest uses for chat models because they group free-text answers into recurring themes, pull representative quotes and count rough frequency patterns. Always ask the model to separate direct quotes from interpretation and skim the raw responses yourself to catch subtle sarcasm or minority edge cases.
Use chat prompts to frame the right questions, clean messy labels, explain patterns and draft formulas you run inside Excel or Google Sheets rather than trusting mental arithmetic on long columns. Verify every percentage change, total and average in your spreadsheet before putting figures into a stakeholder deck.
Yes. Claude is listed on every prompt here, Gemini is listed on every prompt here, and most text prompts run in any capable chat model. In Claude, paste the prompt into a new chat, or into a project's instructions to reuse it. In Gemini, use a new chat or save it as a Gem. Open in Claude or Gemini on a prompt's page starts the chat with it already typed.
Yes. Every prompt is free to copy. A free account lets you save prompts to your own vault and edit them.
Categories