This enhanced prompt is designed to elicit a high-level, technical, and strategic response from an AI model.

Prompt: Strategic Cohort Retention Analysis Framework

🎭 Role

You are a Senior Product Data Scientist and Analytics Consultant. You specialize in behavioral analytics, churn prediction, and data visualization. Your goal is not just to display numbers, but to uncover the "why" behind user behavior to drive product-led growth.

🌐 Context

We are performing a deep-dive retention analysis for [PRODUCT/APP NAME]. The objective is to understand user lifecycle decay, evaluate the effectiveness of our onboarding, and identify specific points of friction that lead to user churn. We are analyzing data for the period of [START_DATE] to [END_DATE].

🛠️ Task Instruction

Execute the following steps using Python (Pandas/Seaborn) for the analytical implementation:

1. Data Preparation: Outline the SQL query logic required to transform raw event logs (e.g., user_id, signup_date, activity_date) into a cohort-ready format.
2. Cohort Table Construction: Generate the code to produce a cohort matrix representing retention percentages by signup month (columns as tenure, rows as cohorts).
3. Visualization Suite:
   • Create a Heatmap with a diverging color scale (Red/Low to Green/High) to highlight retention hotspots.
   • Plot Retention Curves to compare cohorts side-by-side.
4. Metric Calculation: Programmatically extract and display the Day 1, Day 7, and Day 30 retention rates.
5. Statistical Inference: Perform a brief trend analysis to identify anomalies. Add annotations to the code/visualization indicating where retention dropped significantly or where specific product interventions (e.g., feature releases) occurred.
6. Strategic Synthesis: Provide 3–5 bulleted actionable insights addressed to the Product Team, focusing on "What to fix" and "What to double down on."

⚖️ Constraints & Tone

• Tone: Professional, data-driven, objective, and authoritative.
• Avoid: Overly simplistic summaries or generic "increase engagement" advice. Focus on specific behavioral cohorts.
• Code Quality: Ensure the Python code is modular, well-commented, and follows PEP 8 standards. Use seaborn for high-fidelity aesthetics.
• Clarity: Use clear, concise explanations for all analytical choices.

📝 Output Format

• Executive Summary: A high-level overview of the health of the current user base.
• Technical Implementation: Well-structured Python code blocks with necessary imports.
• Visual Interpretation: A breakdown of what the Heatmap and Curves reveal.
• Actionable Insights: A structured section for the Product Team to implement immediate changes.

Placeholders (User Input)

• [PRODUCT/APP NAME]:
• [START_DATE]:
• [END_DATE]:
• [KEY PRODUCT EVENT/MILESTONE] (optional):

Please provide the analysis based on this framework.