Skip to content
Agentic Levels

Everything starts here.

GuestLocal progress only
PreferencesSign in
01Start with one taskBest first move for beginners.02Check your LevelMeasure where you are.03Score an AI resultFind the habit to practice first.04Return to Your WorkScores, links, and checkpoints.
Start here

Begin

HomeThe main entry point.New to AIStart with one useful task.
Know where you are

Measure

Check your LevelUse this after you have tried AI.Fluency ScoreScore an AI result you can review.
Build the habit

Learn

LevelsLessonsTracks
Find the reference

Library

PromptsReferenceResourcesCompare Tools
Turn it into work

Apply

Your Next MoveChoose what AI should change next.Tool SetupGet the tools ready.
Come back later

Return

Your WorkScores, links, and checkpoints.My PathContinue from your level.Updates
Site

Site

PricingAboutFAQ & FeedbackPreferences

© 2026 Fuentes Studio

Privacy·Terms
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

Tracks›Claude Code Fundamentals
Created by potrace 1.16, written by Peter Selinger 2001-2019
L3Lesson 2Free Created by potrace 1.16, written by Peter Selinger 2001-2019

Pick the right surface

Terminal, IDE, desktop, web, or browser control

You ask Claude Code to fix a failing test, from the one surface you always default to. It tells you the fix worked. You believe it, because that surface never showed you the test actually run, and the broken code ships anyway.

18 min · You'll choose the Claude Code surface for one task

You'll match one task to the surface that hands you the clearest proof, instead of defaulting to the one you already know.

0ACTS
  1. Watch the exampleWatchSee it done first
  2. Created by potrace 1.16, written by Peter Selinger 2001-2019 Try it yourselfTry itFill in one blank
  3. Created by potrace 1.16, written by Peter Selinger 2001-2019 Do it on your ownSoloSolo, then check

Before you start

Complete Know when to use Claude Code first.

Remember from Know when to use Claude Code?

One lesson back: what is the one thing you always want before you accept Claude Code's work?

Show one good answer

Proof you can check. A changed file, a command result, or the page rendered. The surface you pick just decides which kind of proof is easiest to see.

The idea

Claude Code can start from more than one place, but the job still decides which place. A surface is where you run it, like the terminal, your code editor, or an app window.

Five possible work surfaces surround one task card with no chosen proof path.
Five possible work surfaces surround one task card with no chosen proof path.
  1. 1Name task proof
  2. 2Needs local commands?Yes→TerminalNo→Needs close file review?
  3. 3Terminal
  4. 4Needs close file review?Yes→IDENo→Needs rendered route proof?
  5. 5IDE
  6. 6Needs rendered route proof?Yes→Browser controlNo→Desktop or web start
  7. 7Browser control
  8. 8Desktop or web start
  9. 9Run command proof
  10. 10Review diff proof
  11. 11Capture route proof
  12. 12Write handoff proof
YesNoYesNoYesNo
Name task proof
1Needs local commands?
Terminal
2Needs close file review?
IDE
3Needs rendered route proof?
Browser control
Desktop or web start
Run command proof
Review diff proof
Capture route proof
Write handoff proof

Surface rule: start with the proof you need, then pick the surface. Command proof points to the terminal, the plain text window where you type commands.

Your code editor, also called an IDE (like VS Code), is closer to a Google Doc for developers than a workshop. It is where you comfortably read and review a change, not usually where you make Claude do the heavy lifting. The actual work often happens in the terminal or the Claude Code CLI, and the IDE is where you open the result afterward to read it in familiar surroundings. Route proof, meaning the finished page rendered, points to a browser you can watch.

If you want one place that does almost everything, the Claude Desktop app is the easiest home base. It holds Claude's chat and Claude Code together in one app, and shows changes side by side as a visual diff (a before and after view), so you can start there and grow into the rest.

TerminalIDEDesktop appWeb / browser
Best forCommands, tests, logsReading and reviewing filesOne home base, chat plus code plus diffsZero-setup single task
SetupCLI installedEditor plus CLIPaid Claude plan onlyNothing, just a browser
Run several at onceYes, one per project tabYes, alongside terminalYes, alongside terminalYes, resumes with --teleport

--teleport resumes a claude.ai/code web session in your local terminal, so a task follows you across surfaces.

People who use this daily rarely run one surface at a time. A real session might mean Claude Code open in a terminal tab for one project, the desktop app open for a second, and a browser tab open on claude.ai/code for a third, all live together. The CLI's own --teleport flag exists for exactly this: it resumes a session that was running on the web right inside your local terminal, so you can pick a task back up wherever you happen to be.

Worked example. A button on your page reads Submit and you want it to say Send.

Claude Desktop
Change the button label on the pricing page from Submit to Send.
Here's the change: Submit -> Send. Only that word updates, nothing else on the page.

Write a message…

Sonnet 4.6High
One word changed, shown side by side, before you accept it.

You open the Claude Desktop app, ask it to change that word, and it shows the old and new side by side. You read it, see only that one word changed, and accept.

Pick the surface that gives Claude Code the right context and gives you the clearest proof.

1

Watch

You type this

Open the Claude Desktop app, go to the Code tab, and change the button label from Submit to Send.

Claude does this

It makes the edit and shows you the old word and the new word side by side as a visual diff. You read the before and after, see that only that one word changed, and click to accept.

Why this works

  • Open the Claude Desktop app

    the proof you want is a before-and-after you can see, and the desktop app shows it without a terminal to learn.

  • go to the Code tab

    that is where Claude Code can read and edit the file, not just talk about it.

  • change the button label from Submit to Send

    one named change stays small enough to read in a single glance.

2

Your turn

The surface to start in

Now a different job. A test keeps failing and I want to watch it run as Claude fixes it. Start in , because that is where I can see the proof I need.

Not the desktop app this time. The proof here is a command running, so which door shows you that?

Show one good answer

the terminal, because the proof you need is the command output, and the terminal is the plain text window where you watch it run.

3

On your own

Think of the last thing you asked an AI to help with. Write a two-line surface card for it: line one, the surface you would start in (terminal, your code editor, the Claude Desktop app, the web, or browser control). Line two, the proof that surface would hand you.

  • I wrote down one starting surface
  • I wrote down the proof it would hand me
  • I did not just default to the surface I always use

Write your own

Loading your workbook…

When this breaks

  • Breaks when the chosen surface cannot access the files, commands, or route needed for proof.
  • Breaks when review happens in the wrong place, like reading a diff for a visual spacing issue.

Created by potrace 1.16, written by Peter Selinger 2001-2019 You can now

✓

You can choose a Claude Code surface from the task

  • ✓You can match proof to terminal, IDE, desktop, web, or browser work
  • ✓You can avoid moving to a heavier surface without a reason
  • ✓You can tell when browser proof is required

Try it from memory

Pulling this out of your own head now is the part that actually moves it into long-term memory. Re-reading just feels like it does.

Think of the last thing you asked an AI to help with. Without looking back, which surface would have fit it best, the terminal, your code editor, the Claude Desktop app, or the web, and what proof would that surface have handed you?

Tap to see one good answer

A good answer ties the surface to the proof. For example, a wording fix on one page fits the Claude Desktop app, because you can see the change side by side as a visual diff and accept it without ever touching a terminal. Command work points to the terminal, and anything you need to see rendered points to the desktop app or a browser.

Key takeaways

The best Claude Code surface is the one that can see the right context and produce the proof you need.

  1. 1Terminal is strongest for commands, logs, tests, and local repo checks.
  2. 2IDE is strongest when you want file review close to the editor.
  3. 3The Claude Desktop app is the easiest all-in-one home base, with chat, code, and visual diffs in one place.
  4. 4Browser control belongs to rendered page proof, not every task.

Created by potrace 1.16, written by Peter Selinger 2001-2019 Go deeper

  • Claude Code CLI reference
  • Claude Code interactive mode

Was this helpful?

Up nextbecause you can pick the door. Next is opening it safely, so the work cannot drift into code you did not mean to touch.Run a first safe session→

Related lessons

What Claude Code actually is: one tool, several surfacesSplit chat work from repo workUse computer use for GUI work
← Back to Claude Code Fundamentals