Colearn
Module 1 · Claude fundamentals for office work

Claude Desktop setup

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

📖 Lesson 1⏱️ ~10 min

You can ask a quick question or hand over a whole office task in one Claude conversation. The capabilities previously called Claude Cowork are becoming part of Claude itself. This course uses Claude Desktop to connect local practice files; web and mobile are useful too. First, install the app and find the message box, permission setting, and model picker.

If you see “Chat” and “Cowork”: Anthropic announced the unified experience on 16 September 2026 and is rolling it out gradually, so the app can look different from one account to the next. If your message box shows separate Chat and Cowork options, choose Cowork for these exercises. If it shows no such choice, simply describe the task. The skills, projects, and connectors you already use carry over. See the announcement and current rollout guidance.

1 · Install it (a couple of minutes)

  1. Go to claude.com/download and download the app for macOS, Windows, or Linux (beta).
  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. You can ask for quick answers and multi-step work from the app.
Before you start: check the current operating-system and plan requirements on the official download page. Managed work computers may also need your organization's approval.

Linux is in beta for Ubuntu and Debian (x64 and arm64). Computer use and dictation are not yet available there; the screenshots below show the macOS interface.

Desktop release channels. On supported macOS and Windows installs, go to Settings → Desktop app → Release channel. Stable is the default and gets updates after more testing. Latest gets updates about once a day and may be less reliable. The selector is unavailable on Linux, Microsoft Store installs, and computers where IT has set a Claude policy. Desktop update guide.

Prefer another language? Look for Language in your profile menu and choose an available interface language. The menu language and the language of your work are separate: you can still write to Claude in your preferred language. Available choices and menu positions can change.

Claude Desktop's 'Choose your language' window: a search box above a three-column list of languages, each shown in its own script and in English — Amharic, Bangla, Bhojpuri, Chinese (Simplified and Traditional), Danish, Dutch, English (United States, selected), Filipino, Finnish, French (France), German (Germany), Gujarati, Hausa and Hindi (India), with more below.
The Choose your language window, as of October 2026 — each language is listed in its own script and in English.
About the screenshots: the desktop examples show the interface used while preparing this course. Labels and available features vary by app version, plan, organization, and rollout. Use them to find the relevant control, then check what your own app offers.
Finding skills and connectors during the Plugins rollout. Checked 10 November 2026: Plugins replaces Customize and its separate tabs. Plugins has been generally available on Free, Pro, Max, Ultra, and Team since 9 November. The Enterprise rollout starts on 30 November. In the new page, open Your plugins → Show all and filter by Skills or Connectors. Existing installations remain. The screenshots show the older layout; use the labels your account offers. Skill creation and upload controls may still use the older skill labels. Official rollout guide.

2 · Where the work runs

Checked on 1 November 2026: new tasks on Pro, Max, and Ultra run in Anthropic's cloud. Older local tasks stay on their original computer. Keep Claude Desktop open and online for access to linked local files, the built-in browser, or computer use.

Unified Claude Enterprise has been generally available since 23 October. For eligible existing organizations that hadn’t already chosen a setting, the unified experience has been on by default since 16 November. See the admin guide. Admins control access; some regulated configurations stay on their existing setup.

Unified Chat and Cowork has been generally available on Claude Team since 12 November 2026 and is already on by default for new Team organizations. On 1 December 2026 it turns on by default for eligible existing organizations that have yet to choose a setting. Owners can turn it on or keep it off in Organization settings → Capabilities. For eligible Team organizations, separate Chat and Cowork options retire on 1 February 2027. Team admin guide.

Plan names: Ultra is the former Max 20x plan. Verified Ultra accounts have no five-hour limit; weekly limits still apply. Check your own usage screen rather than assuming unlimited work.

Local files and cloud work: a folder can stay on your computer while Claude processes copies of the files it needs in the cloud. Keep Claude Desktop open and your computer online when a task needs that folder. Outputs can appear in the session; ask explicitly for a local save when you want one. See Anthropic's current cloud and desktop guidance for your plan.

3 · The project screen, top to bottom

Once you're in, you point Claude 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 window: a left sidebar with Home and Code buttons, Search, New, Projects, Artifacts, Scheduled, Design, Customize and More, plus recent conversations; the 'colearn' project in the middle with the 'New session in colearn' message box; and a right-hand panel with Instructions, Context, Folder, Memory and Scheduled.
The Claude window: your tools on the left, the conversation in the middle, the project's context on the right.
  • Left rail — Home and Recents bring your conversations and longer tasks together; Code is for software development. Start a new conversation and describe the result you need. Below that are your Projects and other tools.
  • Middle — where you work. The project name sits up top (here colearn); under it, the message box ("New session in colearn") — you brief Claude here in plain language, just like writing to a colleague. If the message box shows a Chat · Cowork selector, choose Cowork for these file-based exercises.
  • 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 — Claude "picks up your project context automatically."
The left sidebar: Home and Code buttons at the top, a Search field, then New, Projects, Artifacts, Scheduled, Design, Customize and More.
The left rail, item by item.
  • New — start a fresh conversation (if your message box offers Chat and Cowork, pick Cowork); 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 2.10.
  • Artifacts — saved documents, presentations, and interactive tools Claude builds for you. A static snapshot does not refresh itself; for a connected dashboard, check its source, refresh status, and timestamp.
  • Plugins / 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) — a connected local folder the session can read and save into (lesson 1.3). Check other linked folders, attachments, and enabled tools separately.
  • Mode — how much Claude does without stopping to ask. The next section.
  • Model · effort (here Opus · 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 approval modes you can choose between.
The mode selector: pause-and-approve, or run straight through.
ModeWhat happensUse it when…
Manual ✋Claude asks before using a new tool or opening a new site. Read each request and choose Allow or Deny. Existing permissions can already allow file changes; Manual is not an approval for every individual action.you're new, the task touches important files, or you want to watch the plan and approvals closely.
Auto 🛡️Claude runs on its own without stopping at every step. Automated safety checks run before each action, and it pauses to ask you if anything looks unsafe.the task is low-risk, well understood, and supervised — ideally a routine you've already watched it handle well.
Start cautious. Use Manual for your first tasks — you'll see the plan, the tool use, and the approvals that matter. Once a particular kind of job feels safe and you have narrowed the folder and outcome, Auto is the natural next step: fewer interruptions, with a safety check still running underneath. We come back to deciding what to approve in lesson 1.9. Which mode you start in depends on your plan and app version, so open the selector and pick Manual yourself if it is not already on.
Some versions of the app use longer names ("Manually approve" and "Automatically approve"), and older ones called Manual "Ask before acting". Some accounts and organizations also offer a third mode, "Skip all approvals" (formerly "Act without asking"), which lets Claude act without asking at all. Don't use it for this course: pick the mode that asks before acting.

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: demanding workthe senior specialistthe hardest, most tangled jobs: long multi-step work, careful reasoning, big or messy documents. Often heavier on usage; availability and the default model can change.
Sonnet: everyday workthe reliable all-roundereveryday tasks. Fast, capable, and lighter on your limit than Opus — a smart switch for routine work.
Haiku: quick tasksthe 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 gives it more room to reason and may help on tricky problems, at the cost of time and usage; you still check the result. 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 — Sonnet handles most routine work — and only move up a model or raise effort when a task actually needs it.
Key takeaway: install Claude Desktop, check your plan's setup, and remember the bottom bar. A safe starting point for everything in this course: the default model · default effort, with Manual on. Move to a stronger model for the hard stuff, a faster one for the quick stuff, and to "Auto" only once you trust the routine.

Mini-exercise (3 minutes)

Install Claude Desktop if you haven't, sign in, and complete any setup your app requests. Then just open the mode selector and the model menu to see the options — don't run a task yet. Set it to the default model · default effort and Manual. That's the whole setup — in the next lesson we look at what Claude actually is and the kinds of work you can hand it.