Name Splitter

😫 The Pain Point

You have 1000 contacts with full names in one column (“Nguyen Van An”, “John Smith”). You need separate First, Middle, and Last name columns for your CRM import.

🚀 Agentic Solution

A Smart Name Parser that handles different name formats including Vietnamese names.

Key Features:

• Vietnamese Support: Understands that “Nguyen” is family name (first in Vietnamese convention).
• Multiple Formats: “First Last”, “Last, First”, “First Middle Last”.
• Edge Cases: Handles single names, suffixes (Jr., PhD).

⚔️ Phase 1: Commander (Quick Fix)

For quick parsing.

Prompt:

“I have an Excel contacts.xlsx with column ‘Full_Name’ containing Vietnamese names (format: ‘Last Middle First’, e.g., ‘Nguyen Van An’). Write a Python script using Pandas to:

1. Split: Into ‘Ho’ (Last), ‘Ten_Dem’ (Middle), ‘Ten’ (First).
2. Handle: Names with only 2 parts (Last First) or 1 part.
3. Output: Save as contacts_split.xlsx.

Print sample results for verification.”

Result: Properly structured name data.

🏗️ Phase 2: Architect (Permanent Tool)

Engineering Prompt:

**Role:** Python Tool Developer
**Task:** Create a "Smart Name Parser".

**Requirements:**
1.  **GUI:**
    *   Select Excel file.
    *   Column picker for full name.
    *   Format dropdown: Vietnamese / Western / Auto-detect.
    *   Preview table.
    *   "Apply" button.

2.  **Logic:**
    *   Handle Vietnamese: Last Middle First.
    *   Handle Western: First Middle Last.
    *   Handle edge cases gracefully.

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

🧠 Prompt Decoding

• Vietnamese Names: Family name comes first, given name comes last. Opposite of Western convention.

🛠️ Instructions

1. Copy Prompt → Run.
2. Verify sample output before bulk processing.