Data & Analysis AI prompts

Prompts for working with data without starting from a blank page: cleaning and structuring tables, choosing an analysis, explaining a result in plain language, and writing spreadsheet formulas or queries from a description.

Search these 155 prompts in the app

155 Data & Analysis prompts

Analyze a dataset and find what mattersExplores your data for patterns, segments, and outliers that matter for a decision.
Analyze course completion, quiz results, and learner feedbackTurns LMS completion data, assessment item results, and survey comments into a diagnosis of what to fix in a course.
Analyze donor retention and find lapsed donors to win backA retention analysis using LYBUNT and SYBUNT segments, upgrade and downgrade patterns, and a prioritized win-back plan.
Analyze hotel performance against my competitive setExplains occupancy, ADR, and RevPAR results versus the comp set, with index analysis and the likely causes.
Analyze KPI performanceExplains movement in your KPIs: drivers, risks, and actions.
Analyze loss ratio and combined ratio trends by line of businessA breakdown of what is driving underwriting results, separating frequency, severity, rate, mix, and development effects.
Analyze my clinic's claim denials and revenue cycle KPIsTurns denial and A/R data into root causes, benchmark gaps, and a prioritized fix list for the front end, coding, and billing teams.
Analyze my fleet's CSA safety scores and plan how to lower themExplains which safety categories are driving high scores, which inspections and crashes matter most, and what to fix first.
Analyze my law firm's utilization, realization, and collectionsA law firm financial health review using standard metrics, with the leaks between hours worked and cash collected traced to causes and fixes.
Analyze my recruiting funnel and find where candidates drop offA funnel analysis of pass-through rates, time in stage, and sources that pinpoints bottlenecks and what to fix first.
Analyze patient experience survey results and plan improvementsTurns CAHPS-style scores and patient comments into the few service drivers worth fixing, with owners and a way to tell if fixes worked.
Analyze return reasons and cut my product return rateFinds the SKUs and reasons driving costly returns, from fit to bad photos, and plans fixes with estimated savings.
Analyze survey results with crosstabs, weighting, and significanceA sound quantitative analysis of survey data, with response-bias checks, weighting, crosstabs, and only the differences that are real.
Analyze why we win and lose dealsA win/loss analysis that finds patterns across closed deals and turns them into changes to targeting, process, and messaging.
Audit an Excel workbook for broken, inconsistent, and hard-coded formulasChecks your spreadsheet for formula errors, broken references, inconsistent formulas across rows, and hard-coded numbers that should be formulas.
Audit and retire unused or duplicate dashboardsA plan to inventory BI content, find what's unused or redundant, and retire it safely without breaking anyone's workflow.
Audit the quality of a datasetChecks completeness, accuracy, consistency, and fitness for purpose before you rely on the data.
Automate my monthly Excel report so it refreshes in minutesRedesigns a manual monthly spreadsheet report into a repeatable workflow with Power Query, Tables, and a checklist, staying in Excel.
Balance a production line to meet takt timeTakt time, a station-by-station load chart, and a rebalanced task assignment that cuts the bottleneck and idle time.
Brainstorm and prioritize features for a predictive modelA ranked list of candidate features grounded in the problem, with leakage checks, build effort, and expected signal.
Break down my results into the business drivers behind themBuilds a driver tree from your results, sizes how much each driver contributed to the change, and names which ones to act on.
Break down why a number changed between two periodsA driver breakdown and bridge that shows exactly which segments, volume, price, or mix effects caused a metric to move.
Build a best, base, and worst case scenario model in ExcelTurns your assumptions into a simple Excel scenario model with an inputs tab, a scenario switch, and side-by-side results.
Build a dynamic Excel dashboard from my raw dataPlans a refreshable one-page Excel dashboard for management, with tab layout, KPIs, pivot charts, slicers, and the formulas behind them.
Build a forecast with clear assumptionsA transparent forecast (sales, demand, revenue) with assumptions, scenarios, and sensitivities.
Build a logic model and performance measures for a public programA logic model linking resources to outcomes, with output, outcome, efficiency, and equity measures you can report to councils, legislators, or funders.
Build a monthly performance tracker in ExcelDesigns a reusable monthly tracker with KPIs, targets, month-over-month and year-to-date comparisons, and red/amber/green status.
Build a qualitative codebook from my interview transcriptsDevelops a codebook with definitions, inclusion rules, and examples from my data, ready for consistent coding and thematic analysis.
Build a simple spreadsheet to track ticket sales for an eventStep-by-step setup for a ticket sales tracker with a data entry form, search, totals, and payment status for fundraisers and community events.
Build the right Excel lookup formula with XLOOKUP or INDEX/MATCHGets you a working lookup that pulls values from another table, handles missing matches and multiple criteria, and fits your Excel version.
Calculate and explain earned value (CPI, SPI, and EAC)Works out earned value metrics from your figures and explains in plain words what they say about cost and schedule.
Calculate how much pipeline I need to hit my numberReverse-funnel math that turns your target into required pipeline, opportunities, meetings, and activities by month.
Calculate landed cost to compare domestic and overseas suppliersA side-by-side landed cost model covering freight, duty, inventory carrying, and risk so the cheapest unit price isn't mistaken for cheapest.
Calculate OEE and find where equipment time is being lostAn overall equipment effectiveness (OEE) calculation broken into availability, performance, and quality losses, with priorities to fix.
Catch silent logic errors in a SQL query before sharing resultsFinds the bugs that don't throw errors: join fan-out, dropped rows, null handling, and date boundary mistakes that quietly skew numbers.
Challenge my interpretation of the data and find other explanationsStress-tests your conclusions for alternative explanations, cherry-picking, and averaging traps, then gives you a defensible version.
Check my data for bias before I draw conclusions from itChecks who is missing from your data, how it was measured, and how it is shown, so your conclusion doesn't mislead.
Check my machine learning model for leakage and evaluation mistakesAn audit of how a model was trained and evaluated, catching leakage, bad splits, and misleading metrics before it ships.
Check salaries for unexplained pay gapsAnalyzes pay data within comparable roles to find gaps not explained by legitimate factors and suggests next steps.
Check whether my data is reliable enough to base a decision onA fitness-for-use review that lists the dataset's limitations and which fields, periods, or segments should not drive this decision.
Check whether my data shows causation or just correlationSeparates trend, correlation, and possible causation in your analysis and gives you the strongest claim you can honestly make.
Check whether my KPIs measure activity or real value, and fix themSorts your KPIs into activity, output, and outcome measures, flags vanity metrics, and redesigns the set around the outcomes that matter.
Choose and interpret the right statistical testPicks the right method for your question and data and explains results in plain language.
Choose the right metrics for a PMO portfolio dashboardA focused set of portfolio and delivery metrics with definitions, data sources, thresholds, and the decisions each supports.
Clean a messy datasetA step-by-step cleaning plan for duplicates, missing values, formats, and outliers.
Clean and standardize spreadsheet data with a log of every changeCleans pasted spreadsheet rows, fixes formats and inconsistencies, and gives you a change log plus steps to repeat it in Excel.
Compare freight carrier bids and award shipping lanesNormalizes carrier quotes by lane, scores cost and service, and recommends primary and backup carriers per lane.
Compare performance across periods, teams, or productsSide-by-side performance comparison with drivers of the differences.
Compare performance against targets and find the biggest gapsCompares actuals against targets for every KPI, sizes each gap, and ranks the gaps that matter most so you know where to focus.
Compare two Excel sheets and flag every differenceMatches records between two spreadsheets or lists, flags missing, extra, and changed rows, and gives formulas to reconcile them.
Create a data-quality checklist for a recurring report or datasetA reusable pre-publish checklist with checks, formulas, pass thresholds, owners, and what to do when a check fails.
Create an outcome measurement plan for a nonprofit programIndicators, data sources, collection timing, and responsibilities so you can prove what changed, not just how many people you served.
Cut my fleet's fuel cost per mileFinds where fuel is being wasted by driver, truck, and route, and builds a plan covering idling, speed, purchasing, and fraud controls.
De-identify a dataset before sharing itA plan to remove or mask personal data in a dataset while keeping it useful for analysis, including re-identification risk checks.
Decide whether a volume discount or MOQ is worth acceptingWeighs unit savings against carrying cost, cash, storage, and obsolescence risk to find the order quantity that actually saves money.
Define key risk indicators with thresholdsCreates measurable key risk indicators for my top risks, with data sources, thresholds, escalation paths, and pitfalls to avoid.
Define success metrics and guardrails for a feature launchA primary metric, supporting signals, guardrails, and targets agreed before launch so the result can be judged honestly.
Define the right KPIs and metric definitionsA KPI framework tied to goals, with precise definitions, sources, and owners.
Design a customer health score that actually predicts churnA practical health score model with weighted signals, thresholds, and a plan to test whether it predicts renewals.
Design a dashboard people will actually useA dashboard brief: audience, questions, metrics, layout, and chart choices.
Design a data model for HR reporting and analyticsA warehouse design for HR data with effective dating, clear grain, agreed metric definitions, and access controls for sensitive fields.
Design a one-page company scorecard for my leadership teamA single page of leading and lagging metrics, with owners, targets, and thresholds, that the leadership team reviews every week.
Design a product recommendation system for my online storeA practical plan for personalized product recommendations: approach by data maturity, placements, cold-start handling, and how to measure lift.
Design a star schema for a reporting use caseA dimensional model with fact tables, dimensions, grain, keys, and slowly changing dimension choices for a BI or reporting need.
Design a survey that gets honest, useful answersSurvey questions, scales, and structure that avoid bias and map to the decisions you need to make.
Design an A/B testHypothesis, variants, metrics, sample size, and duration for a valid test.
Design an incrementality or holdout test for a channelA test design that measures whether a channel actually creates extra sales, not just credit for sales that would happen anyway.
Design automated data quality tests for a pipelineA prioritized set of data tests covering freshness, volume, schema, uniqueness, and business rules, with thresholds and owners.
Diagnose a sudden drop in a key product metricA structured investigation plan that rules out tracking errors and narrows down the real cause fast.
Diagnose my digital subscription funnel and reader churnAn analysis of paywall, registration, conversion, and churn data that pinpoints the weakest stage and tests to run next.
Diagnose where our college admissions funnel is losing studentsAnalyzes inquiry-to-enrollment conversion, yield, and summer melt to find where prospective students drop off.
Diagnose why a model is performing worse in productionA step-by-step diagnosis separating data pipeline bugs, input drift, concept drift, and label issues, with a recovery plan.
Engineer my menu using item sales and contribution marginSorts every menu item into stars, plowhorses, puzzles, and dogs, with specific actions for each and the next menu.
Estimate how a price change will affect my salesScenario estimates of how a price change or promotion moves units, revenue, and margin, with an adjusted forecast and a test plan.
Evaluate a statistical forecast's accuracy and explain the missesA backtest and error review of a demand or revenue forecast against simple benchmarks, showing where it misses and how to improve it.
Explain a complicated Excel formula in plain EnglishBreaks down a long or nested Excel formula step by step, says what it actually returns, and points out hidden risks.
Explain a dataset or report in plain business languageExplains what a dataset or report contains, what each column or metric means, and what it shows, in words anyone can follow.
Explain my Excel model to a non-technical executiveTurns a complex spreadsheet or model into a plain-English walkthrough an executive can follow, trust, and question.
Explain what drives a model's predictions to non-technical stakeholdersTranslates feature importance, SHAP values, and model behavior into a plain-English explanation leaders can trust and act on.
Explain, debug, or speed up a SQL, Python, or DAX snippetExplains what an existing query or script does, fixes errors, and optimizes it.
Extract a table from an image or screenshot into a spreadsheetTurn a photo, screenshot, or scanned list into clean tab-separated rows you can paste straight into Excel or Google Sheets.
Find duplicate records in my data, including near-duplicatesFinds exact and fuzzy duplicates, separates them from legitimate repeats, and gives you Excel or SQL steps to resolve them safely.
Find missing values in my data and explain their impactProfiles blanks and placeholder values by column, spots patterns in what's missing, and recommends how to handle each gap.
Find out why overtime is rising and how to cut itAn analysis of overtime data that separates demand, staffing, and process causes, with targeted actions to reduce it.
Find recurring patterns across incidents, complaints, or ticketsAnalyzes a pasted list of incidents, complaints, or tickets to find the patterns, clusters, and repeat causes behind them.
Find the 20% of activities driving 80% of my resultsRuns a Pareto analysis to show the few activities, customers, or products producing most of your results, and what to cut or double down on.
Find the activation metric that predicts customer retentionA method to identify the early actions that separate retained users from churned ones, and how to drive them.
Find the biggest leak in my product funnelA step-by-step funnel analysis that pinpoints the costliest drop-off and the likeliest fixes to test.
Find the few causes behind most of my defects or complaintsA Pareto analysis of defect, complaint, or delay data that shows which few causes to fix first.
Find the root cause of repeated stockoutsWorks through demand, parameters, lead time, and execution data to pinpoint why items keep running out, with specific fixes.
Find what drove my store's weekly sales resultBreaks a store's sales variance into traffic, conversion, ATV, and UPT, then gives specific actions for next week.
Find what extra data would strengthen my analysisReviews your analysis and data to pinpoint the missing information that would most improve confidence, and how to get it.
Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.
Find where deals leak out of my sales funnelA stage-by-stage conversion and velocity analysis that pinpoints where deals stall or drop, and why, with targeted fixes.
Find where my construction jobs are losing moneyA job cost review comparing estimate to actual by cost code, with over/under billing and profit fade explained and fixes listed.
Flag impossible or suspicious values in my dataChecks your data against logic and business rules for impossible, placeholder, and implausible values, and gives reusable validation rules.
Forecast a delivery date range from team velocityUses your backlog size and past throughput to give a realistic date range instead of a single promised date.
Forecast the next few months from historical data in ExcelBuilds a simple, explainable forecast from your past numbers, with trend and seasonality, a range, and the Excel steps to reproduce it.
Frame a business problem as a machine learning projectTurns a business goal into a well-posed ML problem with target, unit of prediction, success metric, baseline, and a go or no-go check.
Get up to speed on an unfamiliar data warehouse quicklyA structured plan and question list to map a new company's data warehouse, find trusted tables, and avoid common traps.
Group students for intervention from screening and assessment dataSorts students into MTSS or RTI tiers and intervention groups from universal screening and diagnostic results.
Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
Interpret A/B test results correctlyReads out a test result: significance, practical impact, caveats, and a decision.
Justify my sample size with a power analysisWorks through a power analysis with defensible effect-size assumptions and writes the sample size justification for my methods or proposal.
Make sense of conflicting attribution data across channelsA clear explanation of why your ad platforms, analytics, and CRM disagree, and a practical way to report credit.
Measure and improve my sales forecast accuracyAn analysis of how accurate past forecasts were, where bias comes from, and the process changes that tighten the number.
Measure the impact of a change when an A/B test isn't possibleChooses and plans a quasi-experimental method like difference-in-differences or synthetic control, with assumptions and checks.
Pick the three insights and five numbers my executives needRanks your findings down to the single most important insight, the top three, the five numbers to watch, and the biggest surprise.
Plan a category assortment with a clear good-better-best rangeKeep, add, drop, or online-only decisions for every SKU, a price ladder, and store clustering, based on sales, margin, and space.
Plan an RNA-seq differential expression analysisA reproducible, step-by-step RNA-seq workflow from raw reads to differentially expressed genes, with QC checkpoints and common pitfalls flagged.
Plan markdowns to clear seasonal stock while protecting marginA SKU-by-SKU markdown cadence based on weeks of supply and sell-through, with the margin impact of each price cut.
Plan row-level security for a BI reportA row-level security design that maps users to the data they may see, with roles, rules, testing steps, and edge cases.
Prepare a quarterly people review for the business leader I supportTurns your client group's HR data into a concise quarterly review with insights, risks, and recommended actions for the leader.
Read my SPC chart and process capability resultsA plain-English read of a control chart and Cp/Cpk results: whether the process is stable, capable, and what to do next.
Recommend the pivot tables and charts to build from my spreadsheetSuggests the most useful pivot tables and charts for your data, with exact field placements and what each one will reveal.
Reconcile two reports that show different numbersPinpoints why two dashboards or reports disagree on the same metric and gives a fix plus a short explanation for stakeholders.
Review my analysis for errors before it goes outA rigorous second-pair-of-eyes check of an analysis for logic, data, statistical, and communication mistakes, ranked by severity.
Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
Run a sensitivity analysis on my financial model's key driversA sensitivity and break-even analysis that shows which assumptions really move the outcome and by how much.
Set chargeability targets by staff level and test firm profitabilityA model linking chargeable hours, billing rates, leverage, and salaries by level to show whether a professional services firm makes its target margin.
Set the right list price for my home from comparable salesA price range based on comparable sales and market speed, with a pricing strategy and a plan for when to adjust.
Set up a UTM and campaign naming conventionA consistent tagging and naming system so campaign data is clean, comparable, and easy to report on.
Set up data validation rules in Excel to stop bad entriesCreates a validation framework for your spreadsheet: allowed values, dropdowns, check columns, and an exceptions report that catches bad data.
Set up metric alerts that catch real problems without false alarmsDesigns monitoring alerts for key business metrics with sensible thresholds, seasonality handling, and clear routing so people trust them.
Solve an Excel or Google Sheets problemGets you the right formula, pivot, or approach — with an explanation you can reuse.
Speed up a slow Power BI or Tableau dashboardDiagnoses why a BI report loads slowly and gives a ranked list of fixes across data model, queries, calculations, and visuals.
Spot anomalies and outliers in dataFinds unusual values and patterns and separates real signals from data errors.
Spot slipping work in a task tracker exportAnalyzes your Jira, Asana, or spreadsheet export to find overdue, stalled, and at-risk work before it hits a milestone.
Standardize inconsistent names and categories in my dataBuilds a mapping table that cleans up spelling, case, abbreviation, and naming variants, plus a naming convention going forward.
Summarize a model validation for model risk managementA validation report summary covering conceptual soundness, data, performance, limitations, and findings with severity ratings.
Test that a migrated report or pipeline matches the old oneA parity-testing plan for migrations that compares old and new outputs at the right level, with tolerances and sign-off criteria.
Trace data lineage across SQL scripts and stored proceduresMap where each table's data comes from and goes to, so you can see what breaks before you change a table.
Turn a business question into testable hypothesesA prioritized backlog of hypotheses with the data needed to test each.
Turn a manual Excel report into an automated BI reportA migration plan from a recurring spreadsheet report to an automated, refreshable report, preserving the logic people rely on.
Turn a raw spreadsheet into a management-ready report with an executive summaryConverts raw spreadsheet data into a clear report for managers: executive summary, key numbers, tables, and recommended actions.
Turn a vague data request into a clear analysis planConverts a fuzzy stakeholder ask into a scoped plan with the real question, data needed, deliverable, and clarifying questions.
Turn an analysis into a story people act onShapes analysis into a clear narrative with one message and supporting evidence.
Turn my analysis findings into a clear recommendationConverts findings into options, a recommended choice, trade-offs, assumptions, and success metrics a decision-maker can act on.
Turn my comps into a pricing recommendation for a sellerA comparative market analysis with adjusted comps, a recommended list-price range, and a plain-English explanation for the seller.
Turn my monthly or quarterly numbers into an executive business reviewTurns your numbers into an executive business review: headline, performance vs. plan, drivers, risks, and decisions needed, as a report or slides.
Turn numbers into business insightsTranslates figures into what they mean, why they matter, and what to do.
Understand an inherited Excel workbook and map what it doesMaps a spreadsheet you inherited: what each tab does, how data flows, which cells are inputs, and where it could break.
Write a chart specification I can build in Excel or Power BIA build-ready chart spec covering chart type, data mapping, scale, emphasis, labels, and accessibility for the message you need to show.
Write a data dictionary for a table or datasetProduces clear column-level documentation with definitions, types, allowed values, grain, and known caveats so others can use the data safely.
Write a model card to document a machine learning modelA complete model card covering intended use, data, performance by segment, limitations, fairness checks, and monitoring plan.
Write a monthly IT and security report for leadershipTurns ticket, uptime, and security metrics into a short report showing trends, risks, and decisions needed.
Write a monthly owner report for a managed rental portfolioA clear owner-facing report covering occupancy, collections, delinquencies, maintenance spend, and decisions needed.
Write a pre-registration and analysis plan for my studyDrafts a pre-registration covering hypotheses, sampling, variables, analysis decisions, and exclusion rules before data collection.
Write a SQL query from plain EnglishTurns a business question into SQL, with validation checks and an explanation.
Write an analytics event tracking plan for a featureAn engineer-ready event spec with names, triggers, properties, and the questions each event answers.
Write an Excel formula to categorize records automaticallyBuilds the formula and lookup table that auto-assigns categories, bands, or tiers to each row based on your rules.
Write an Excel formula to extract text, numbers, or dates from messy cellsPulls the piece you need out of combined or messy cells, like codes, names, domains, or dates, with a formula that handles exceptions.
Write commentary for a dashboard or KPI reportWrites the 'so what' narrative executives need alongside a dashboard — for sales, marketing, HR, finance, ops, or support.
Write the caveats and limitations section of my analysisAn honest, readable limitations section that explains uncertainty and data gaps without burying the conclusion.
Write up statistical results in proper reporting styleTurns software output into a correctly formatted results section with effect sizes, confidence intervals, and matching tables.

Data & Analysis AI prompts

155 Data & Analysis prompts

Other topics