kappa 1ebe765691 Replace pattern-based agent routing with AI intent classification ...

Instead of regex patterns to detect user intent, use a lightweight AI
call (classifyIntent) that categorizes messages into troubleshoot,
onboarding, billing, asset, or general. This catches ambiguous
expressions like "example.com 좀 봐주세요" that patterns would miss.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-12 02:38:55 +09:00

src

Replace pattern-based agent routing with AI intent classification

2026-02-12 02:38:55 +09:00

tests

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

.gitignore

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

CLAUDE.md

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

package-lock.json

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

package.json

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

schema.sql

Add RAG semantic search and proactive event notifications

2026-02-11 18:09:13 +09:00

tsconfig.json

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

vitest.config.ts

Initial implementation of Telegram AI customer support bot

2026-02-11 13:21:38 +09:00

wrangler.toml

Update wrangler.toml with actual D1, KV namespace IDs

2026-02-11 18:35:06 +09:00

Description

Telegram AI 고객 지원 봇 (Cloudflare Workers + Hono + D1 + Workers AI)

198 KiB

Languages

TypeScript 99.8%

Shell 0.2%