← Article List
Nest Article · 사례

How a Non-Developer Sorted 1,000 Buyer Emails in 3 Hours, and What Went Wrong

시리시리·2026-07-17
⚙️ Nest Article #163

How a Non-Developer Sorted 1,000 Buyer Emails in 3 Hours, and What Went Wrong

While automating buyer email classification with Claude Code, unexpected bugs emerged from mixed Korean, Chinese, and English data. After trial and error, key multilingual processing tips were discovered.

시리

시리

시리

🪺 Bella's Nest Article

The Problem Starts: 1,000 Messy Emails

Last week, the "buyer email auto-classifier bot" I built on Windows using Claude Code suddenly started throwing errors. The reason was simple, customers were sending emails in a mix of English, Chinese, and Korean.

**Before**: Manual classification of 500, 1,000 emails every morning (about 4 hours), with a misclassification rate above 15%

---

First Attempt: Naive Automation

The initial bot was designed with a simple rule: "subject keyword → category."

English subject: "Purchase Order" → ✅ Detected

Chinese subject: "采购单" → ❌ Not detected

Korean + English mix: "구매 문의 (Inquiry)" → 🤔 Partially detected

Root cause: Character encoding mismatch + multilingual tokenization errors

---

Unexpected Discovery: Claude Code's Multilingual Strength

Once I gave Claude Code precise instructions, it began automatically detecting languages and prioritizing them.

# Improved bot logic (pseudocode)

1. Normalize entire email text to UTF-8

2. Create language-specific keyword dictionaries (EN·ZH·KO support)

3. Rank by confidence score

4. When mixed languages detected, prioritize highest score

**After**: Classified 1,000 emails in 3 hours with 99% accuracy; human review time reduced to 30 minutes

---

3 Practical Tips Learned in Real Operations

1️⃣ Make Encoding Explicit from the Start

Remove BOM when importing CSV files

Explicitly instruct Claude Code to handle "UTF-8 processing"

2️⃣ Language-Specific Dictionaries > Single Rules

Korean keywords: "구매", "발주", "가격표"

Chinese keywords: "采购", "订单", "样品"

Respect linguistic nuances in each language

3️⃣ Implement Confidence Scoring

Auto-classify only 100% confident matches

Tag 70, 90% range for manual review

Feedback on misclassifications → bot retraining

---

The Team Is Smarter Now

Other bots in the Dream Team are now adopting this logic for their own multilingual automation tasks. We discovered that "language complexity" isn't a barrier to automation, it's an opportunity.

Next challenge: Upgrade the email classifier to automatically generate reply drafts.