Skip to content
zero2vibecodelearn vibe coding
Level 0 · Install and first run 6 min Reviewed by the author · Aug 4, 2026

How a turn works

Every piece of work with an agent is the same four beats: you ask, it plans, it edits, you review. Learning where you sit in that loop is most of the job.

Level 0 · 0 / 4 lessons0%

No hands-on task in this lesson — just read it through and answer the questions.

Whatever you are building, a turn has the same four beats.

1. You ask

One request, in plain English, about one thing.

Add a Clear button under the todo list that empties it.

Specific beats clever. You do not need magic words, a persona, or a template. You need to say what you want in a sentence you would be comfortable saying to a colleague.

The most common beginner mistake is asking for five things at once. Then when something is wrong you cannot tell which of the five caused it.

2. It plans

Before touching anything, a good turn starts with the agent saying what it intends to do: which files it will open, what it will change, what it thinks the tricky part is.

You can ask for this explicitly — tell me the plan first, do not change anything yet — and Claude Code also has a where exploring and proposing happen but edits are held back until you approve. Level 1 covers it properly.

Read the plan for one thing above all: did it understand the request? If the plan is aimed at the wrong file, you have just saved yourself twenty minutes for the price of reading four lines.

Quick check

The plan says it will edit a file you did not expect. What is the cheapest response?

3. It edits

Now it changes files. Depending on how you have set things up, it will either ask before each action or apply edits as it goes — Claude Code has modes for both, and level 3 is where you choose deliberately.

It may also run commands: your tests, a build, a script. It reads the output and reacts to it. That is not a gimmick; an agent that can run the test suite can catch its own mistakes before you ever see them.

4. You review

The agent shows you what changed as a : the lines it removed and the lines it added.

Read it. Every time. Three questions, in order:

  1. Is this what I asked for? Not “is it good code” — is it the thing.
  2. Did it change anything I did not ask about? Extra “improvements” are how surprises get in.
  3. Does it run? Start the thing, click the button, run the tests.

The honest failure mode

It will sometimes call a function that does not exist, import a library you do not have, or use an option that was never in that API. It will do this in fluent, confident, well-formatted code. The only reliable detector is running it — reading alone catches maybe half.

Then you go around again

Almost. The button clears the list but the counter still shows the old number.

That sentence is a whole turn. Short, specific, one problem. Three or four of these and the feature is done — and you understood every step, because you were in the loop for each one.

When the loop stops working

If you have gone around three times on the same problem and it is not converging, stop. Do not go round a fourth. Level 2 has a whole lesson on why starting over beats correcting five times, and it is one of the most useful habits in this course.

Do I have to review if the tests pass?
Is it faster to write one huge, detailed prompt?

Try it yourself

One full turn, all four beats. The last one is the easiest to skip and the most expensive to skip.

Check your understanding

Answered 0/3
Mode:

Which step of the loop is yours and cannot be delegated?

What is the point of asking for a plan before any code?

The agent says it made a change. What is the correct next move?

Finish the task in the terminal and answer the questions to complete the lesson.

📝 My notes

Saved automatically in this browser · shows up on the Notes page.

Lesson Q&A

Which step of the loop is yours and cannot be delegated?

The agent can propose and it can act. Deciding whether the result is acceptable is the one part that has to be you.

What is the point of asking for a plan before any code?

Catching a misunderstanding at the plan stage is the cheapest correction available to you.

The agent says it made a change. What is the correct next move?

Asking a model if it is sure gets you a confident answer either way. Reading the change and running the code gets you the truth.

The plan says it will edit a file you did not expect. What is the cheapest response?

One sentence now, at plan stage, is the smallest correction available anywhere in this loop.

Move between lessons with · search with ⌘K