Blog
Claude Code 101
"Agentic Coding Tool"인 Claude Code가 왜, 어떻게 동작하는지 핵심 원리부터 제대로 정리
Completed Anthropic's official Claude Code 101 course to understand why Claude Code is built as an Agentic Coding Tool rather than a chat tool — and how it actually works under the hood.
Key concepts covered:
- Agentic Loop & Context Window — how Claude Code …
Read more →
Claude 101 Course Notes
Claude 제품 전반의 기능과 실무 활용법을 체계적으로 정리한 강의 수강 노트
Completed Anthropic's official Claude 101 course, part of the Anthropic Academy curriculum, and put together notes on what stood out.
The course walks through Claude's core surfaces with concrete, real-world examples rather than abstract feature lists:
- Three working modes — a clear breakdown of when …
Read more →
AI Agent: E2E Test
URL 하나만 주면 크롤링부터 테스트 시나리오·코드 생성·실행·리포트까지 이어지는 E2E 테스트 파이프라인
An end-to-end test pipeline that takes a single URL and automatically crawls the site, drafts natural-language test scenarios, generates runnable Jest+Playwright test code, and produces an HTML report — no site-specific hardcoding.
Key design decisions: - A general-purpose BFS crawler instead of a hardcoded page …
QA AgentRead more →
LangGraph + HITL
주제와 조건을 입력하면 여러 에이전트가 병렬로 조사하고, 쓰고, 검토한다 — 품질이 미달이면 interrupt()로 멈추고 사람의 판단을 기다린다.
Built a multi-agent pipeline that generates a lecture plan from a 6-field input (topic, audience, duration, delivery method, tools, constraints) using LangGraph + FastAPI + Gemini API + Tavily.
The pipeline runs in 3 rounds: sequential planning → parallel web research → sequential writing → …
AgentRead more →
Multi-Agent(HITL) with n8n
주제와 조건을 입력하면 AI가 조사하고, 쓰고, 세 관점으로 검토한다 — 품질이 미달이면 Slack으로 사람에게 판단을 넘긴다.
Built a multi-agent pipeline that automatically generates a lecture plan from a 6-field webhook input (topic, audience, duration, delivery method, tools, constraints). n8n orchestrates the full workflow across 20 nodes; a Flask server handles all Gemini and Tavily calls.
The pipeline runs in 3 rounds: …
AgentRead more →