Colearn
Module 1 · Claude Cowork Fundamentals

Claude Desktop setup

A few minutes of setup, then a tour of the main screen you will use every day

📖 Lesson 1 ⏱️ ~10 min

Claude Cowork is not a website you log into — it lives inside the Claude Desktop app, the same app that holds Claude Chat. Before anything else, let's get it installed, let it set itself up once, and learn the main screen you will use every day: the message box, the autonomy switch, and the model picker.

1 · Install it (a couple of minutes)

  1. Go to claude.ai/download and download the app for macOS or Windows.
  2. Open the downloaded file and install it like any other app, then launch it (Applications on a Mac, the Start menu on Windows).
  3. Sign in with your Anthropic account — the same login you use on claude.ai. That's it: Chat and Cowork are both inside this one app.
What you need: macOS 11 (Big Sur) or newer, or Windows 10 or newer. The app itself is small and quick to install.

Prefer another language? Claude Desktop's interface — its menus and buttons — comes in a handful of languages. Open Settings and choose yours from the language list:

Claude Desktop's interface-language menu, listing English (United States, selected), Français, Deutsch, हिन्दी, Indonesia, Italiano, 日本語, 한국어, Português (Brasil), Español (Latinoamérica) and Español (España).
The interface languages Claude Desktop offers, as of June 2026.
As of June 2026 the interface is available only in these languages: English, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese (Brazil), and Spanish (Latin America & Spain). If yours isn't on the list, the app simply stays in English — but that's only the buttons. You can still write to Claude in your own language, and it understands and replies in it. The interface language and the language you actually work in are two separate things.

2 · The first time: Claude sets up its workspace

The first time you open Cowork, it builds a small, private workspace on your computer — an isolated mini-environment where it safely runs its tools (opening a spreadsheet, generating a PDF, and so on). You'll see a one-time "Setting up Claude's workspace…" progress bar. Let it finish; you only do this once.

On Windows — a one-time switch: this workspace runs in a lightweight virtual machine, which needs a built-in Windows feature called Virtual Machine Platform. If it's turned off, Claude shows "Virtual Machine Platform not available" and offers to enable it for you — click through, and Windows may ask you to restart once. After that, the workspace sets itself up and you're done. On a Mac there's nothing to enable.

3 · The project screen, top to bottom

Once you're in, you point Cowork at a folder to work in (that folder, the working folder, is the whole of lesson 1.3) and you land on the project screen. It splits into three calm regions.

The full Claude Desktop Cowork window: a left sidebar with Chat, Cowork and Code tabs plus New task, Projects, Scheduled and Recents; a centre column with the project name 'colearn' and the 'What would you like to work on in this project?' message box; and a right panel with Instructions, Scheduled, and Context showing the project's working folder on your computer plus Memory.
The Cowork window: your tools on the left, the conversation in the middle, the project's context on the right.
  • Left rail — the Chat · Cowork · Code switch at the top (all three live in this one app; this course is the Cowork tab), plus New task, your Projects, and Recents. The rest of the rail is broken down item by item below.
  • Middle — where you work. The project name sits up top (here colearn); under it, the message box "What would you like to work on in this project?" — you brief Claude here in plain language, just like writing to a colleague.
  • Right rail — the project's context. Context shows the working folder on your computer (lesson 1.3) and the project's Memory; Instructions is where you set house rules for how Claude works here. You can ignore these at the start — Cowork "picks up your project context automatically."
The Cowork left sidebar: Chat, Cowork and Code tabs at the top, then New task, Projects, Scheduled, Live artifacts, Dispatch (marked Beta) and Customize, with Scheduled and Recents sections below.
The left rail, item by item.
  • New task — start a fresh task in the current project; one task = one focused thread of work.
  • Projects — every project you've set up, each with its own working folder, instructions, and memory.
  • Scheduled — tasks that run by themselves on a timer; you'll build one in lesson 2.7.
  • Live artifacts — interactive pages Claude builds for you (a tracker, a dashboard) and refreshes when you open them.
  • Dispatch (Beta) — send Claude a task from your phone and it runs here, on this computer (lesson 2.7).
  • Customize — where skills, connectors, and plugins are managed; lesson 1.11 is all about it.
  • Recents — your latest tasks, so you can jump back into anything you were doing.

Now look closer at the slim bar right under the message box — it carries the controls you'll touch most often.

A close-up of the message box and the bar beneath it: a plus button bottom-left, a microphone bottom-right, and along the bottom the working folder, an autonomy mode chip, and the model and effort selector.
The bar under the message box: attach (+), dictate (mic), and your three controls — folder, mode, model · effort.
  • The + (bottom-left of the box) — attach extra files or context to a single message.
  • The microphone (bottom-right) — dictate your request instead of typing.
  • The working folder (the colearn chip) — the one folder this session can see and save into (lesson 1.3).
  • Mode — how much Claude does without stopping to ask. The next section.
  • Model · effort (here Sonnet · Medium) — which Claude does the work, and how hard it thinks. Section 5.

4 · The mode selector — how much leash you give it

Click the mode selector (the chip showing the current mode) and you get two ways for Claude to work. This is the single most important setting for feeling in control, especially at the start. It does not change the folder you granted access to; it changes how often Claude pauses when a step needs explicit approval.

The mode selector open, showing the cautious approval mode and the faster act-without-asking mode.
The mode selector: pause-and-approve, or run straight through.
ModeWhat happensUse it when…
Ask before actingClaude pauses when a step needs your approval — especially outside-world actions such as connected tools, browser actions, or changes beyond the approved working folder.you're new, the task touches important files, or you want to watch the plan and approvals closely.
Act without askingClaude works through the approved task without stopping at every step. Permanent deletion and similarly hard-to-undo actions still require explicit confirmation.the task is low-risk, well understood, and supervised — ideally a routine you've already watched it handle well.
Start cautious. Use Ask before acting for your first tasks — you'll see the plan, the tool use, and the approvals that matter. Switch to Act without asking only once a particular kind of job feels safe and you have narrowed the folder and outcome. We come back to deciding what to approve in lesson 1.9.

5 · Choosing a model (and effort)

Open the model control on the right of the bottom bar and you can pick which Claude does the work — plus how hard it thinks. There's no wrong choice; it's a trade-off between speed and depth.

The model menu open, listing several Claude models, an effort setting, and a usage-limit notice.
The model menu: pick a model, pick an effort level, and keep an eye on usage.
Model choiceThink of it as…Best for
Opus: the most capablethe senior specialistthe hardest, most tangled jobs: long multi-step work, careful reasoning, big or messy documents. Usually slower and heavier on usage.
Sonnet: the defaultthe reliable all-rounderalmost everything, day to day. Fast and capable — the right pick unless you have a reason to change.
Haiku: the fastestthe quick assistantsimple, short, or repetitive tasks where speed matters and you want to spend the least of your limit.

Effort is a separate dial: how thoroughly Claude thinks before it acts. Higher effort means more careful, better on tricky problems — but slower. For this course, start with the default model at its default effort, raise effort for genuinely hard reasoning, and lower it for obvious tasks. More models simply lets you reach other available models if you ever need a specific one.

Watch your usage. Heavier models and higher effort use up your plan's weekly allowance faster. The habit that saves you: pick the lightest setup that still does the job well, and only reach for Opus or High effort when a task actually needs it.
Key takeaway: install Claude Desktop, let the workspace finish setting up once, and remember the bottom bar. A safe starting point for everything in this course: the default model · default effort, with Ask before acting on. Move to a stronger model for the hard stuff, a faster one for the quick stuff, and to "Act without asking" only once you trust the routine.

Mini-exercise (3 minutes)

Install Claude Desktop if you haven't, open it, and let the workspace finish setting up (on Windows, allow the Virtual Machine Platform step and restart if asked). Then just open the mode selector and the model menu to see the options — don't run a task yet. Leave it set to the default model · default effort and Ask before acting. That's the whole setup — in the next lesson we look at what Claude Cowork actually is and the kinds of work you can hand it.