Vibe Coding · 강의

에이전트 도구: Claude Code와 Copilot

사용자를 대신해 코드를 읽고 쓰고 실행하는 도우미를 활용합니다.

에이전트 도구: Claude Code와 Copilot은(는) CoddyKit의 무료 Vibe Coding 강의입니다. 이것은 4개 중 2번째 강의입니다. 아래에서 전체 강의를 무료로 읽을 수 있으며, 내장 코드 에디터와 24/7 AI 튜터와 함께 브라우저에서 직접 실습할 수 있습니다. 이 강의는 Vibe Coding 학습 경로의 일부이며, 진행 상황이 웹과 CoddyKit 앱에 동기화됩니다. Vibe Coding 강의에는 총 4개의 강의가 포함되어 있습니다.

이 강의의 일부는 아직 번역되지 않았으며 영어로 표시됩니다.

Beyond Autocomplete

Some AI tools don't just suggest code — they act. They read your files, write new ones, run commands, and check the results, all from a single instruction.

These are agentic tools. The two you'll hear about most are Claude Code and GitHub Copilot. Think of them as a teammate you can delegate whole tasks to.

What 'Agentic' Means

A normal assistant answers a question. An agent takes a goal and works toward it in multiple steps — reading, writing, running, and adjusting.

Tell an agent 'add a contact form to my site' and it will find the right file, write the form, wire up the button, and tell you what it changed. You supervise; it does the legwork.

Claude Code: The Terminal Agent

Claude Code is Anthropic's agent that runs in your terminal (and inside editors too). You type a request in plain English, and it explores your project, edits files, and can run commands like installing packages or starting your app.

It's powerful because it works across many files at once and explains each step as it goes.

In Claude Code you might type:

"Add a dark mode toggle to my web app. Update the HTML, CSS and JavaScript so clicking it switches between light and dark themes."

Letting Claude Code Run Things

The magic of an agent is that it can run code and read the output. If your app errors, Claude Code can run it, see the error, and fix it — looping until it works.

For safety, it asks before doing anything important, like deleting files or running commands. You approve each risky step.

"Run my project, and if there are any errors in the console, fix them and run it again until it works."

GitHub Copilot

GitHub Copilot started as smart autocomplete — it suggests the next line as you type. It has since grown a chat and an agent mode that can make multi-file changes too.

It's built right into editors like VS Code, so the suggestions appear inline as faint 'ghost text' you accept with a key press.

Copilot's Ghost Text

As you type a comment or a function name, Copilot guesses the rest. You'll see grey suggested text — press Tab to accept it.

This is great for momentum: write a clear comment describing what you want, and let Copilot fill in the code below it.

// add two numbers and return the result
function add(a, b) {
  return a + b;
}

console.log(add(3, 4));

Comment-Driven Building

A neat trick with Copilot: write your intent as a comment first, then let the AI implement it. Your comments become a kind of prompt.

Clear comments lead to clear code — vague ones lead to guesses. The clearer you describe the goal, the better the suggestion.

// show a friendly greeting based on the time of day
function greeting(hour) {
  if (hour < 12) return "Good morning!";
  if (hour < 18) return "Good afternoon!";
  return "Good evening!";
}

console.log(greeting(9));

Claude Code vs Copilot

Both are agentic, but they shine in different moments:

Claude Code — best for big, multi-step tasks and running/fixing code end-to-end. Strong reasoning, terminal-native.
Copilot — best for fast inline suggestions while you're already typing in your editor.

Many builders use both: Copilot for flow, Claude Code for the heavy lifting.

The Supervise-and-Approve Loop

With agents you're the manager, not the typist. The healthy loop looks like this:

Describe the goal clearly.
Let the agent plan and act.
Read what it changed (the diff).
Approve, or ask for a fix.

You stay responsible for the result — the agent just moves fast.

Writing Good Instructions

Agents reward clear, complete instructions. Tell them the goal, any constraints, and how you'll know it worked.

A strong agent instruction reads almost like a small task ticket — specific enough that there's only one reasonable way to do it.

"Create a new file called todo.html with a simple to-do list: an input box, an 'Add' button, and a list below it. Adding an item should clear the input. Use only plain HTML, CSS and JavaScript in one file."

When to Reach for an Agent

Use an agent when a task is bigger than a single line:

Building a feature that spans several files.
Fixing an error you can't figure out.
Setting up or running a project.
Refactoring or renaming across the codebase.

For tiny inline tweaks, plain autocomplete is often enough.

Quick Check

What makes a tool like Claude Code 'agentic' rather than just an autocomplete?

Recap: Delegating to Agents

Agentic tools turn you into a manager of code:

Claude Code runs in the terminal, handles multi-step tasks, and can run/fix code.
Copilot gives fast inline suggestions and has an agent mode too.
Write clear instructions; review every diff; approve risky steps.

Next: browser-based app builders like v0, Bolt and Lovable that go from prompt to running app instantly.

자주 묻는 질문

“에이전트 도구: Claude Code와 Copilot” 강의는 무료인가요?

네 — “에이전트 도구: Claude Code와 Copilot” 전체 내용을 이 웹사이트에서 무료로 읽을 수 있습니다. 인터랙티브하게 실습하려면(내장 코드 에디터와 24/7 AI 튜터), CoddyKit PRO로 업그레이드하면 Vibe Coding 강의 전체를 잠금 해제할 수 있습니다. Vibe Coding 강의에는 총 4개의 강의가 포함되어 있습니다.

“에이전트 도구: Claude Code와 Copilot”에서 뭘 배우나요?

사용자를 대신해 코드를 읽고 쓰고 실행하는 도우미를 활용합니다. 브라우저에서 직접 실행하는 실습 코드로 Vibe Coding을(를) 배우며, 24/7 AI 튜터가 강의를 진행하면서 질문에 답변해줍니다.

Vibe Coding을(를) 시작하는 데 경험이 필요한가요?

사전 경험은 필요하지 않습니다. CoddyKit의 Vibe Coding은(는) 초급자부터 고급 학습자까지를 위해 구성되어 있으므로, 여기서 시작하거나 처음부터 시작할 수 있으며 자신의 속도대로 진행할 수 있습니다. 이것은 4개 중 2번째 강의입니다.

“에이전트 도구: Claude Code와 Copilot” 강의는 얼마나 걸리나요?

대부분의 CoddyKit 강의는 약 5~10분이 소요됩니다. 각 강의는 간결하고 인터랙티브하여 꾸준한 진행이 가능하며, 웹과 앱에서 중단한 부분부터 바로 시작할 수 있습니다.

이 Vibe Coding 강의에서 코드를 작성하고 실행할 수 있나요?

네. 모든 Vibe Coding 강의에는 내장 코드 에디터가 포함되어 있으므로, 브라우저에서 바로 실제 코드를 작성하고 실행한 후 즉시 AI 피드백을 받을 수 있습니다 — 로컬 설정이 필요 없습니다.

이 강의의 모든 강의

← Vibe Coding(으)로 돌아가기