Blog AI & HCI
Single vs Multi-Agent
에이전트를 여러 개로 쪼갠다고 항상 더 똑똑해지는 건 아니다
Before scaling an agentic workflow into a multi-agent pipeline, it's worth asking whether the added complexity actually pays off in token cost.
Single-agent overhead accumulates vertically — context grows turn by turn, but prompt caching keeps reuse efficient. Multi-agent overhead spreads horizontally — each sub-agent …
AgentRead more →
Multi-Agent with Claude Code
주제와 조건을 입력하면 9개 서브에이전트가 조사하고, 쓰고, 검토하고, 고친다 — 코드 없이
Built a multi-agent pipeline that automatically generates a lecture plan from a natural language prompt. No code — orchestrated entirely through CLAUDE.md (entry point only, 3 lines) and agent definition files (.claude/agents/*.md).
The pipeline runs in 4 rounds: sequential planning → parallel web research (up …
AIRead more →
ReAct Research Agent with Lang
n8n 캔버스에서 화살표로 그렸던 루프를, 코드 한 줄의 그래프 선언으로 옮겼다.
Reimplemented the same ReAct (Reasoning + Acting) research agent from the n8n
version, this time as an explicit graph in LangGraph. Where n8n expressed the
loop as a line drawn back to an earlier node on a canvas,
add_conditional_edges expresses the same logic in code. …
Read more →
ReAct Research Agent with n8n
주제 하나만 던지면, AI가 스스로 검색하고 판단하고 — 부족하면 다시 검색한다.
Built a ReAct (Reasoning + Acting) agent that autonomously repeats search and judgment until it has enough information to answer a research topic. Unlike a single-pass pipeline, this agent decides for itself whether to search again or stop, using Gemini for judgment and Tavily for …
AIRead more →
Claude Code Practical Guide
챗봇이랑 뭐가 달라요? 물어보는 사람이 많아서 정리했다.
A practical reference guide for Claude Code — the terminal-based AI coding agent by Anthropic. Covers the key difference from the chat interface, essential commands, and common gotchas that trip up first-time users.
Core concept: Claude Code runs in your terminal and acts directly on …
AIRead more →