Vibe Coding · Lezione

Da assistente ad agente

Quando l'IA agisce, non si limita a rispondere

Da assistente ad agente è una lezione Vibe Coding gratuita su CoddyKit. Questa è la lezione 1 di 4. Puoi leggere la lezione completa qui gratuitamente — poi esercitati direttamente nel browser con un editor di codice integrato e un tutor IA disponibile 24/7. Fa parte del percorso di apprendimento Vibe Coding, e i tuoi progressi si sincronizzano tra il web e l'app CoddyKit. Il corso Vibe Coding include 4 lezioni in totale.

Parti di questa lezione non sono ancora state tradotte e vengono mostrate in inglese.

When AI Stops Talking and Starts Doing

So far you've used AI like a chat partner: you ask, it answers, you copy the code. That's an assistant.

An agent is different. You give it a goal, and it acts on its own: it reads files, runs commands, checks results, and keeps going until the job is done. You're no longer the one pasting everything.

This lesson is about that leap: from AI that answers to AI that does the work.

Assistant vs Agent

The simplest way to feel the difference:

Assistant: "Here's the code for a login form" — you take it from there.
Agent: "I created login.html, wired up the form, ran the app, and it works." — it did the steps.

Tools like Claude Code and Cursor's agent mode are agentic: they touch your real project files, not just a chat box.

The Agent Loop

Under the hood, an agent runs a simple loop: think → act → observe → repeat.

It plans a step, takes an action (edit a file, run a command), looks at what happened, then decides the next step. It keeps looping until your goal is met or it gets stuck.

Here's that loop sketched as JavaScript pseudo-code so you can picture it:

function agentLoop(goal) {
  let done = false;
  while (!done) {
    const plan = think(goal);   // decide next step
    const result = act(plan);   // edit file / run command
    done = check(result, goal); // is the goal met?
  }
  return "Goal reached!";
}
console.log("An agent repeats: think, act, observe.");

What a Goal Looks Like

You don't micromanage an agent. You hand it an outcome and let it figure out the steps.

Compare a single instruction to an agent goal: the goal describes the finished result, not each keystroke.

Goal for an agent (paste into Claude Code or Cursor agent mode):

"Add a dark mode toggle to my website. Create a button in the top
right, switch the page between light and dark colors when clicked,
and remember the choice when the user comes back. Test it works
before you finish."

Agents Use Your Real Project

The big shift: an agent works inside your actual files. It can open index.html, find your CSS, add new code, and save — all without you copy-pasting.

That's powerful and a little scary. It means the agent can change a lot at once, so you'll learn to review what it did (and you'll cover safety in the last lesson of this course).

Agents Can Run Things

Beyond editing files, agents can run commands: start your app, install a package, or run tests. Then they read the output and react.

If a command fails, a good agent notices the error and fixes it — no need for you to copy the red text into chat. This is why agents feel like a teammate, not a tool.

Example agent goal that involves running things:

"Install the dependencies for this project, start the dev server,
open the homepage, and tell me if there are any errors in the
console. If there are, fix them and run it again."

Watching an Agent Work

When you run an agent in Claude Code or Cursor, you'll see it narrate its steps: "Reading file... editing... running... done."

This is your window into its thinking. Read it! If it heads in the wrong direction, you can stop it and steer. You stay the pilot; the agent just flies the plane for the boring parts.

Approve Before It Acts

Most agent tools ask for permission before doing something risky — like deleting files or running an unknown command. They show you the action and wait for a yes.

Treat every approval as a real decision. "Allow once" for normal edits is fine; pause and read carefully before approving anything that removes or overwrites a lot.

Good Tasks for an Agent

Agents shine on tasks with many small, mechanical steps:

Renaming something across many files
Adding a feature that touches several places
Fixing a bug, running the app, confirming it's gone
Setting up a new project from scratch

For a one-line question ("what does this function do?"), a plain assistant chat is faster. Match the mode to the job.

You Set the Goal, AI Walks the Path

Here's the mindset to carry forward: you own the goal and the judgment; the agent owns the legwork.

You decide what success looks like and check the result. The agent handles the how — the dozens of little steps in between. That partnership is the heart of vibe coding at the next level.

Try this framing for any agent request:

GOAL:    what the finished result should be
CONTEXT: which project / files it should work in
DONE WHEN: how the agent knows it succeeded

Fill those three in and you've written a great agent task.

Your First Agent Mindset

Before the quiz, picture it: instead of asking "how do I add a contact form?" and copying code, you say "Add a working contact form to my site and confirm it submits."

Same idea, totally different workflow. The agent reads your project, builds it, tests it, and reports back. You review and approve. That's agentic building.

Quick Check

Let's make sure the assistant-vs-agent difference clicked.

Recap: From Answering to Acting

You've made the leap in mindset:

An assistant answers; an agent acts on a goal.
Agents run a think → act → observe loop on your real files.
You hand over a goal (and a "done when"), not every step.
Watch and approve — you stay the pilot.
Tools like Claude Code and Cursor agent mode make this real.

Next up: giving your agent tools so it can reach the web, files, and code.

Domande Frequenti

La lezione «Da assistente ad agente» è gratuita?

Sì — il testo completo di «Da assistente ad agente» è gratuito qui sul web. Per esercitarvi in modo interattivo (un editor di codice integrato e un tutor IA 24/7) e sbloccare il resto del corso Vibe Coding, passa a CoddyKit PRO. Il corso Vibe Coding include 4 lezioni in totale.

Cosa imparerò in «Da assistente ad agente»?

Quando l'IA agisce, non si limita a rispondere Eserciti Vibe Coding con codice pratico che esegui direttamente nel browser, e un tutor IA 24/7 risponde alle tue domande mentre lavori sulla lezione.

Ho bisogno di esperienza per iniziare Vibe Coding?

Non è richiesta alcuna esperienza precedente. Vibe Coding su CoddyKit è strutturato per principianti e studenti avanzati, quindi puoi iniziare da qui o dall'inizio e procedere al tuo ritmo. Questa è la lezione 1 di 4.

Quanto tempo richiede la lezione «Da assistente ad agente»?

La maggior parte delle lezioni CoddyKit richiede circa 5–10 minuti. Ogni lezione è breve e interattiva, quindi fai progressi costanti e riprendi esattamente da dove hai lasciato su web e app.

Posso scrivere ed eseguire codice in questa lezione Vibe Coding?

Sì. Ogni lezione Vibe Coding include un editor di codice integrato, quindi scrivi ed esegui codice reale direttamente nel tuo browser e ricevi feedback istantaneo dall'IA — nessuna configurazione locale necessaria.

Tutte le lezioni di questo corso

← Torna a Vibe Coding