AI Data Analysis Workflow

I need to analyze [dataset description]. Business question: [what decision will this inform?]. Data fields: [list columns with types]. Help me: frame 3-5 specific analytical questions, identify which fields are most relevant, flag potential data quality issues to check, suggest the analysis approach for each question, and estimate if the data is sufficient to answer the questions confidently.

Write [Python/R/SQL] code to clean and prepare this dataset for analysis. Schema: [describe]. Known issues: [list any known problems]. Handle: missing values (recommend strategy per field: impute/drop/flag), outlier detection and treatment, data type conversions, feature engineering (create useful derived fields), and create a clean summary table. Include data quality report at each step.

Analyze this cleaned dataset to answer: [list questions from step 1]. Write [Python/R] code for: descriptive statistics, correlation analysis, hypothesis tests where applicable, trend analysis over time, segment comparisons, and create publication-quality visualizations for each key finding. Use [matplotlib/seaborn/plotly]. Annotate charts with key takeaways.

Write an insights summary from this data analysis. Findings: [paste key results with stats]. Audience: [who will read this]. For each insight: state the finding in plain language (no jargon), explain why it matters for the business, quantify the opportunity or risk, recommend a specific action, and note confidence level and caveats. Lead with the most impactful finding.