Customer Classifier

😫 The Pain Point

You have 10,000 customers and need to segment them by purchase frequency. VIP (>10 orders), Regular (3-10), New (1-2), Inactive (0 in 6 months). Doing this manually is error-prone.

🚀 Agentic Solution

A Rule-Based Classifier that categorizes based on your business logic.

Key Features:

• Custom Rules: Define your own thresholds.
• Multiple Criteria: Combine amount, frequency, recency.
• RFM Analysis: Built-in Recency-Frequency-Monetary scoring.

⚔️ Phase 1: Commander (Quick Fix)

For quick classification.

Prompt:

“I have an Excel customers.xlsx with columns ‘Customer_ID’, ‘Order_Count’, ‘Total_Spent’, ‘Last_Order_Date’. Write a Python script using Pandas to:

1. Classify:
   • VIP: Order_Count > 10 AND Total_Spent > 10M
   • Regular: Order_Count 3-10
   • New: Order_Count 1-2
   • Inactive: Last_Order > 6 months ago
2. Add: New column ‘Segment’.
3. Output: Save with segment counts summary.

Print distribution of segments.”

Result: Segmented customer list for marketing.

🏗️ Phase 2: Architect (Permanent Tool)

Engineering Prompt:

**Role:** Python Tool Developer
**Task:** Create a "Customer Segmentation Tool".

**Requirements:**
1.  **GUI:**
    *   Select Excel file.
    *   Rule builder: Column, Operator, Value.
    *   Multiple rules with AND/OR.
    *   Preview segment distribution.
    *   "Apply" button.

2.  **Logic:**
    *   Parse rules into Pandas queries.
    *   Handle date comparisons.
    *   Show segment statistics.

3.  **Deliverables:**
    *   `customer_classifier.py`
    *   `run.bat`, `run.sh`
    *   `requirements.txt`

🧠 Prompt Decoding

• RFM Analysis: Recency (when), Frequency (how often), Monetary (how much) - standard marketing segmentation.

🛠️ Instructions

1. Copy Prompt → Adjust thresholds → Run.