ChatGPT Prompts for Data Analysts

<context> I work with a [TOOL] database (e.g. PostgreSQL, BigQuery, Snowflake). The relevant tables and columns are: [PASTE SCHEMA: table names, columns, types, and key relationships] </context> <task> Write a single SQL query that answers: "[YOUR QUESTION IN PLAIN ENGLISH]". 1. Use only the tables and columns I listed — never invent fields. 2. Match [TOOL]'s exact SQL dialect and date/window-function syntax. 3. Add a one-line comment above each non-trivial clause explaining what it does. 4. List any assumptions you made (e.g. how you defined [METRIC], how you handled NULLs). 5. Flag any place where my schema looks ambiguous and ask before guessing. </task>

<context> This [TOOL] query is [returning wrong results / erroring / running slowly]: [PASTE QUERY] The error message or unexpected output is: [PASTE ERROR OR DESCRIBE WHAT IS WRONG] Table sizes / row counts: [APPROX ROW COUNTS PER TABLE] </context> <task> 1. Diagnose the most likely cause of the problem in plain language. 2. Provide a corrected version of the full query. 3. List the specific changes you made and why each one fixes the issue. 4. If it is a performance problem, suggest indexes, partition pruning, or rewrites and estimate the impact. 5. Give me one quick test query to confirm the fix returns the expected [METRIC]. </task>

<context> I need to move this query from [SOURCE TOOL] to [TARGET TOOL]: [PASTE QUERY] </context> <task> 1. Rewrite the query to run natively on [TARGET TOOL]. 2. Replace any dialect-specific functions (date math, string functions, window frames, array/JSON handling) with the [TARGET TOOL] equivalent. 3. Call out any function that has no direct equivalent and propose a workaround. 4. Note any behavioural differences (e.g. NULL ordering, integer vs float division) that could change results for [METRIC]. 5. Keep formatting and aliases identical so I can diff the two versions. </task>

<context> My team keeps rewriting near-identical queries against [DATASET] for different date ranges, segments, and filters. Schema: [PASTE RELEVANT TABLES/COLUMNS] </context> <task> 1. Write one parameterized [TOOL] query (or CTE-based template) that computes [METRIC] with placeholders for date range, segment, and filter values. 2. Clearly label each parameter and show an example invocation. 3. Structure it with named CTEs so each step is readable and testable. 4. Add inline comments so a junior analyst can adapt it safely. 5. Suggest how to turn this into a saved view or macro in [TOOL]. </task>

<context> I inherited this [TOOL] query and need to understand it before I change it: [PASTE QUERY] </context> <task> 1. Summarize in 2-3 sentences what business question this query answers and what [METRIC] it produces. 2. Walk through it CTE by CTE (or subquery by subquery) in plain English. 3. Identify the grain of the final output (one row per what?). 4. Flag anything risky: fan-out joins, hardcoded dates, deduplication logic, or filters that silently drop rows. 5. Suggest 2-3 safe improvements without changing the result. </task>

<context> I have a dataset [DATASET] with these columns and sample rows: [PASTE COLUMN NAMES + 10-20 SAMPLE ROWS, OR A DESCRIBE/PROFILE OUTPUT] </context> <task> 1. For each column, infer its likely type, role (id, dimension, measure, date), and expected value range. 2. Flag data-quality risks: missing values, mixed formats, outliers, inconsistent categories, duplicates, suspicious zeros. 3. Rank the issues by how badly they could distort [METRIC]. 4. Recommend a concrete cleaning step for each issue. 5. Give me a short checklist I can run before trusting this data in a report. </task>

<context> Dataset: [DATASET]. The issues I need to fix: [LIST ISSUES, e.g. dates in 3 formats, "N/A" used for nulls, trailing whitespace, duplicate ids] I want the cleaning done in [TOOL] (e.g. SQL, pandas, dbt). </context> <task> 1. Write [TOOL] code that fixes each listed issue, one clearly-labeled step per issue. 2. Standardize dates, trim/normalize text, coerce real nulls, and dedupe on the correct key. 3. Preserve a record count before and after each step so I can audit row loss. 4. Add comments explaining each transformation. 5. Warn me about any step that could silently drop or alter rows feeding [METRIC]. </task>

<context> The column [METRIC or DIMENSION] in [DATASET] has inconsistent free-text values, for example: [PASTE DISTINCT VALUES, e.g. "USA", "U.S.A.", "United States", "us"] </context> <task> 1. Propose a clean canonical set of categories. 2. Build a full mapping table from every raw value to its canonical value. 3. Write [TOOL] code (CASE statement or mapping join) to apply it. 4. Flag any raw values that are genuinely ambiguous and ask me how to map them. 5. Suggest a guardrail to catch new unmapped values in future loads. </task>

<context> My dataset [DATASET] is currently in [wide / long] format. Sample: [PASTE A FEW ROWS] I need it in [long / wide] format because [REASON, e.g. to chart a time series / to feed a model]. </context> <task> 1. Show the exact target structure (columns and one example row). 2. Write [TOOL] code (pivot/unpivot, melt/pivot_table, or SQL CASE) to reshape it. 3. Explain how each original field maps into the new shape. 4. Handle edge cases: missing combinations, duplicate keys, and aggregation when needed. 5. Verify the reshape didn't change the total of [METRIC]. </task>

<context> I load [DATASET] into [TOOL] on a [daily/hourly] schedule and feed it into reports that track [METRIC]. Key columns and expected rules: [DESCRIBE KEYS, RANGES, AND BUSINESS RULES] </context> <task> 1. Propose a set of automated data-quality tests (row counts, null thresholds, uniqueness, referential integrity, range checks, freshness). 2. Write each test as runnable [TOOL] code (or dbt tests / assertions). 3. Define a clear pass/fail threshold for each. 4. Recommend which failures should block the pipeline vs. just alert. 5. Suggest how to log results so I can track data quality over time. </task>

<context> [METRIC] [rose/fell] by [AMOUNT] over [TIME PERIOD] in [DATASET]. Available dimensions to slice by: [LIST DIMENSIONS, e.g. region, plan, channel, device, cohort] </context> <task> 1. Propose a structured approach to decompose the change (e.g. mix vs. rate, segment contribution, before/after). 2. List the specific slices and queries I should run, in priority order. 3. For each, state the hypothesis it would confirm or kill. 4. Tell me how to distinguish a real driver from a composition/Simpson's-paradox effect. 5. Give me a template sentence to report each finding to stakeholders. </task>

<context> I want to analyze [retention / repeat behavior / LTV] for [DATASET]. Relevant events and timestamps: [DESCRIBE EVENT TABLE: user id, event type, timestamp, value] We care most about [METRIC]. </context> <task> 1. Define the cohort grain (signup week, first-purchase month, etc.) and recommend the best one for my question. 2. Write the [TOOL] SQL to build the cohort/retention matrix. 3. Explain how to read the resulting table and what a healthy vs. concerning pattern looks like. 4. Suggest 2-3 segment breakdowns that usually reveal the most. 5. Note common pitfalls (survivorship bias, partial last period) and how to handle them. </task>

<context> Claim to test: "[STATE THE HYPOTHESIS, e.g. the new onboarding lifted activation]". Data available: [DESCRIBE GROUPS, SAMPLE SIZES, AND THE METRIC, e.g. [METRIC] for treatment vs. control]. </context> <task> 1. State the appropriate statistical test and why (t-test, chi-square, Mann-Whitney, etc.). 2. List the assumptions that test makes and how to check them with my data. 3. Tell me exactly what numbers to compute and provide [TOOL] code to do it. 4. Explain how to interpret the result, including effect size, not just the p-value. 5. Warn me about confounders, peeking, and multiple-comparison traps relevant to this claim. </task>

<context> Here is a time series (or table) of [METRIC] from [DATASET]: [PASTE THE DATA OR UPLOAD THE FILE] Context about the business: [ANY EVENTS, LAUNCHES, SEASONALITY, OUTAGES] </context> <task> 1. Identify points that deviate meaningfully from the trend or seasonal pattern. 2. For each anomaly, give the magnitude and the date/segment. 3. Propose the most plausible explanations, separating likely real signal from likely data issues. 4. Recommend the follow-up query or slice that would confirm each explanation. 5. Tell me which anomalies are worth escalating now vs. monitoring. </task>

<context> A stakeholder asked me: "[PASTE THE VAGUE REQUEST, e.g. why are sales down]". Data I have access to: [LIST DATASETS / TABLES]. Audience for the answer: [WHO + WHAT THEY DECIDE]. </context> <task> 1. Restate the underlying decision this analysis should inform. 2. List the 3-5 sharpest questions I should actually answer. 3. For each, specify the [METRIC], the slice, and the data source. 4. Define what "done" looks like and what would change the stakeholder's decision. 5. Draft 3 clarifying questions I should ask the stakeholder before I start. </task>