Data Analysis Prompts

You are a meticulous data analyst. Here is a sample of my raw dataset (header row plus a few rows): {{sample_rows}} Context: this data describes {{data_description}} and I plan to...

You are a senior Python data engineer. Write clean, reproducible pandas code to clean my dataset. Columns and their meaning: {{column_spec}} Known issues to handle: {{known_issues}...

Act as a data analyst guiding me through exploratory data analysis. Dataset summary: {{dataset_summary}} My goal / the question I care about: {{analysis_goal}} Produce an EDA plan...

You are a SQL expert writing for a {{sql_dialect}} database. Here is the relevant schema (tables, columns, types, keys): {{schema}} Question to answer: {{question}} Rules: - Use on...

You are a SQL reviewer. Explain and debug the query below. Dialect: {{sql_dialect}} What I expected it to return: {{expected_result}} What is actually wrong (if known): {{symptom}}...

You are a database performance specialist for {{sql_dialect}}. Slow query: {{query}} Context: - Approximate row counts of the main tables: {{table_sizes}} - Existing indexes: {{ind...

You are a data analyst. I will paste a dataset (CSV or table). Produce a clear statistical summary a non-technical reader can follow. For each numeric column: count, missing %, min...

You are a data storyteller helping me brief {{audience}}. Here are my results (tables, metrics, or chart descriptions): {{results}} Business context: {{context}} Produce: 1. The si...

You are a data visualization expert. I want to show: {{message_to_convey}} The variables involved: {{variables_involved}} My audience: {{audience}} Where it will be shown: {{medium...

Write {{library}} code in Python to create this chart. Data source: a DataFrame named df with these columns: {{columns}} Chart I want: {{chart_description}} Requirements: - Correct...

You are a spreadsheet formula expert for {{spreadsheet_tool}}. My data layout: {{layout}} What I want to calculate: {{calculation}} Return: 1. The formula, ready to paste, using th...

Explain this {{spreadsheet_tool}} formula in plain English. Formula: {{formula}} Context: it sits in cell {{cell}} and the surrounding data is {{data_context}}. Do this: 1. Break t...

You are a spreadsheet analyst. Help me build a pivot table. My source columns: {{columns}} The question I want the pivot to answer: {{question}} Tool: {{spreadsheet_tool}} Tell me:...

You are an experimentation analyst. Interpret this A/B test honestly. Metric tested: {{metric}} Control: {{control_numbers}} Variant: {{variant_numbers}} Test duration and sample s...

You are a statistics tutor. Help me pick the correct statistical test. My question: {{question}} The variables and their types (continuous, categorical, paired, etc.): {{variables}...

You are a statistician. Interpret this regression output for a business reader. Model type: {{model_type}} Outcome variable: {{outcome}} Output (coefficients, standard errors, p-va...

You are an applied ML lead. Help me frame this as a machine learning problem. Business goal: {{business_goal}} Data I have available: {{available_data}} How a prediction would be u...

You are a feature engineering expert. Suggest features to improve a model that predicts {{target}}. Raw columns available: {{columns}} Domain context: {{domain_context}} For each s...

You are a forecasting analyst. Help me forecast {{metric}}. History available: {{history_description}} Granularity and horizon I need: {{granularity_and_horizon}} Known drivers, se...

You are a data analyst hunting for anomalies. Here is the data or distribution for the column {{column}}: {{data}} Context: this column represents {{column_meaning}}. Do this: 1. I...

You are a BI designer. Spec a dashboard for {{audience}} whose main job is {{audience_job}}. The key questions they need answered: {{key_questions}} Data available: {{available_dat...

You are an analytics lead writing a metric definition. Metric name: {{metric_name}} What the team wants it to capture: {{intent}} Data sources and relevant fields: {{data_sources}}...

You are a product analyst. Help me run a cohort analysis for {{product_or_metric}}. Data available (events, users, timestamps): {{data_description}} What I want to learn: {{questio...

You are a growth analyst. Help me analyze this conversion funnel. Funnel steps in order: {{steps}} Counts or rates at each step: {{step_numbers}} Context (product, traffic source,...

You are a customer analytics expert. Help me segment customers. Available attributes and behaviors: {{attributes}} The decision the segments will drive: {{business_use}} Provide: 1...

You are a careful data analyst. Interpret this correlation matrix. Variables and what they mean: {{variable_meanings}} The matrix: {{matrix}} Do this: 1. List the strongest positiv...

You are a senior analyst who scopes work before touching data. The request as I received it: {{request}} Data I can access: {{available_data}} Who is asking and what they will deci...

You are a data steward. Write a data dictionary for this table. Table name: {{table_name}} Sample rows and any notes I have: {{sample_and_notes}} For every column, infer and docume...

You are a research analyst. Analyze these open-ended survey responses about {{survey_topic}}. Responses: {{responses}} Do this: 1. Group responses into clear themes and give each a...

You are a skeptical peer reviewer. Pressure-test my analysis before I present it to {{audience}}. My analysis, method, and conclusions: {{analysis}} The data and any caveats: {{dat...

You are a senior SQL developer working with {{database}}. Here are the relevant tables and columns: {{schema}} I want to answer this question: {{question}} Write a single SQL query...

You are a patient data engineer explaining SQL to a junior analyst. Here is a query I need to understand: {{query}} Do the following: 1. Give a one-sentence summary of what the que...

You are a database performance specialist for {{database}}. This query is slow: {{query}} Context about the data: {{data_context}} Do the following: 1. Identify the most likely bot...

You are a SQL debugging expert for {{database}}. My query: {{query}} The error message: {{error}} Do the following: 1. Explain in plain language what the error actually means. 2. I...

You are a SQL mentor helping me join tables correctly. Tables and their key columns: {{tables}} I want to produce a result that has: {{desired_result}} Do the following: 1. Recomme...

You are a SQL expert specializing in window functions for {{database}}. My table: {{schema}} I want to calculate: {{calculation}} Do the following: 1. Write the query using the app...

You are an expert in multiple SQL dialects. This query is written for {{source_dialect}}: {{query}} Rewrite it so it runs correctly on {{target_dialect}}. Do the following: 1. Prov...

You are a data analyst starting EDA on a new dataset. Dataset description: {{dataset_description}} Columns and types: {{columns}} Goal of the analysis: {{goal}} Produce a step-by-s...

You are a statistics tutor who explains things clearly. Here is a summary statistics table: {{stats_table}} Context about the data: {{context}} Do the following: 1. Explain what ea...

You are a data cleaning specialist. Here is a sample of my messy data and its problems: {{data_sample}} Tool I will clean it in: {{tool}} Produce a cleaning checklist that covers:...

You are a data analyst advising on missing data. Column: {{column_name}} What it represents: {{column_meaning}} Share of rows missing: {{missing_percent}} How I plan to use this da...

You are a data analyst handling outliers. Column and what it measures: {{column_description}} A few of the extreme values I see: {{extreme_values}} Analysis goal: {{goal}} Do the f...

You are a data visualization expert. The data I want to show: {{data_description}} The single point I want the viewer to take away: {{message}} Audience: {{audience}} Do the follow...

You are a data visualization reviewer. Here is a description of my chart (or paste the image): {{chart_description}} What it is meant to communicate: {{intended_message}} Review it...

You are a data translator who explains data to non-technical people. Dataset summary or sample: {{data}} Who will read this: {{audience}} Write a plain-English summary that covers:...

You are a senior analyst who turns numbers into decisions. Here are my analysis results: {{results}} Business context and what we care about: {{context}} Do the following: 1. State...

You are a spreadsheet formula expert for {{tool}}. My data layout: {{layout}} What I want the formula to do: {{goal}} Do the following: 1. Give the exact formula to paste into a ce...

You are a spreadsheet troubleshooting expert for {{tool}}. My formula: {{formula}} The error or wrong result I get: {{problem}} What I expected to happen: {{expected}} Do the follo...

You are an analyst who builds clear pivot tables in {{tool}}. My source columns: {{columns}} The question I want the pivot to answer: {{question}} Do the following: 1. Tell me exac...

You are a Python data analyst who writes clean pandas code. My DataFrame columns and dtypes: {{columns}} What I want to do: {{task}} Do the following: 1. Write the pandas code, ass...