AI 에이전트란 무엇이고, 무엇으로 이루어지는가
두루뭉술한 설명 없이 용어만 정리했습니다. 에이전트가 실제로 무엇인지, 무엇이 고객 앞에 내놓을 만한 에이전트를 만드는지, 콘솔의 각 항목이 무슨 일을 하는지.
여기서 시작하세요
이게 대체 무엇인지, 그리고 "우리 GPT 쓰는데요"가 왜 같은 말이 아닌지.
What is an AI agent?
Software that can hold a conversation, look things up, and take actions on your systems — deciding for itself which of those to do next.
읽기AI agent vs LLM: what is the difference?
The model is the engine that turns text into text; the agent is everything built around it — retrieval, tools, memory, boundaries and channels. Models are replaceable parts inside an agent.
읽기What is a business AI agent?
An agent that works for a specific business — answering from that company's own documents, inside a scope its owner defines, and accountable for what it says.
읽기무엇으로 이루어지는가
콘솔에서 설정하는 다섯 가지와, 각각이 맡는 역할.
What is an agent's soul (system prompt)?
The standing description of who an agent is — its character, tone and non-negotiables — held separately from the job it happens to be doing.
읽기What is a knowledge base for an AI agent?
The documents an agent may answer from. agent4.io keeps two kinds — your company's vetted material, and each customer's own files — retrieved together but never confused for one another.
읽기What is an agent Skill?
A named capability pack — a short description of when to use it, fuller instructions, and the tools it unlocks — that the agent loads only when it becomes relevant.
읽기What is MCP (Model Context Protocol)?
The Model Context Protocol — an open standard for connecting an agent to external tools and data, so a system exposes its capabilities once instead of once per AI product.
읽기Knowledge base, tools or Skill — which does what
Three different jobs that get confused for one — the knowledge base holds facts, an MCP tool performs a calculation you cannot let a model improvise, and a Skill is the procedure that decides which to reach for.
읽기Fine-tuning vs RAG: when you actually need to fine-tune
Continuing a model's training on examples of the behaviour you want, so that behaviour becomes its default instead of something you ask for on every request. It changes how a model works, not what it knows.
읽기어떻게 움직이는가
아무도 입력하기 전에, 그리고 모두가 떠난 뒤에 에이전트가 스스로 하는 일.
What is a page playbook (page-aware AI chat)?
A per-page briefing for the agent — background it should already know, an opening line, and a few suggested questions — chosen automatically from the URL the visitor opened the chat on.
읽기What are scheduled tasks for an AI agent?
Work an agent commits to for a specific future moment — a follow-up it decides to send, or a recurring reminder — executed on time by a scheduler rather than waiting for someone to speak first.
읽기What are ask forms (forms inside the chat)?
A small form the agent composes mid-conversation — choices, a number, a date — rendered as something to tap rather than a paragraph of questions to answer by typing.
읽기What is a space (agent workspace)?
The isolated container holding one customer's conversations, documents and memory — enforced at the database level, so one customer's material cannot surface in another's conversation.
읽기실제로 가동하기
대부분의 파일럿이 멈춰 서는 지점, 그리고 꼭 그러지 않아도 되는 이유.