How to Use Claude Cowork: A Getting-Started Walkthrough (2026)

TL;DR. Claude Cowork is the "do it for me" version of Claude, included in Claude Pro. To actually use it: (1) get Pro and open Cowork on desktop, (2) create a Project (this gives it a folder and memory), (3) open a task inside that Project and describe an outcome in plain English, (4) review and approve as it works. No code. The whole skill is learning to delegate clearly and to keep a checkpoint on anything irreversible.

If you've read what Claude Cowork is and want to actually start using it, this is the practical walkthrough. It takes about ten minutes to get going.

Step 1 — Get access

Claude Cowork is included on every Claude plan — even Free. There's no separate "Cowork" purchase; paid plans (Pro, about $20/month, and Max) add much higher usage limits and unlock plugin installs. Sign in at claude.ai, then open the Claude desktop app — Cowork lives there, because it works with your real files and apps, which a browser tab can't do.

Step 2 — Create a Project before you do anything else

This is the step people skip, and it's the most important one. A Project is a persistent workspace: it has its own folder, its own instructions, and its own memory. That's what lets Cowork remember your context instead of starting cold every time.

Open Cowork → Projects → create a new one. Name it for the work you'll do there ("My Client Work," "Marketing," "My Practice"). Cowork attaches a folder to it automatically. Anything that needs to stick around — files you're working on, a saved profile, instructions — lives in that folder.

Why it matters: tools and plugins that run outside a Project can't save state between tasks. If you ever install a plugin that asks you to "run the setup wizard" and it can't find a Project, this is why. Make the Project first.

Step 3 — Give it your first real task

Open a task inside your Project and describe an outcome, not a step. Good first tasks are small and low-stakes:

• "Here are my rough meeting notes — turn them into a clean summary with action items."
• "Organize the files in this folder by type and date, and show me the plan before you move anything."
• "Draft a friendly reply to this email in my voice." (Paste the email.)

Notice the pattern: you say what you want, give it the context (the notes, the folder, the email), and let it work. This is the same skill as writing a good prompt — be clear about the goal, the context, and the format.

Step 4 — Watch it work, and approve the consequential steps

Cowork plans the steps and starts doing them. For anything reversible (drafting, organizing, summarizing), let it run. For anything irreversible or outward-facing — sending an email, deleting files, posting publicly — it should pause and ask. Say yes when you mean yes. This human checkpoint is what keeps Cowork safe: it drafts and prepares freely, but you approve what actually leaves your computer.

Step 5 — Add skills and plugins (optional)

Out of the box, Cowork is a capable generalist. You can make it a specialist by installing Agent Skills — small instruction packs that activate automatically for specific tasks. Anthropic offers free ones, and there are paid profession packs (like the packs on this site) that turn Cowork into, say, a financial-advisor or bookkeeper assistant. Skills install into your Project and run on the Claude plan you already have — no extra per-use fee. You can browse profession-specific plugins here.

Your first 3 tasks to try

Step 3 covered the pattern; here are three day-one tasks, fully worked, so you can see what actually comes back. Drop a real file or folder into your Project first, then paste the prompt.

1. Organize a messy folder.

"Look at the files in my Downloads folder. Group them by type, rename them clearly with dates, and flag any obvious duplicates. Show me the plan before you move anything."

Cowork scans the folder, proposes a tidy structure (e.g. Invoices/, Receipts/, Drafts/), and lists which files it would rename or delete. You approve, and it does it. You get back: a sorted folder and a short note of what changed — nothing moved without your yes.

2. Turn rough notes into a report.

"Here are my notes from this morning's client call. Turn them into a clean one-page summary with a short recap, decisions made, and action items with owners." (Paste or point to the notes.)

Cowork reads the notes, pulls out the structure, and drafts a formatted document. You get back: a saved summary file in your Project folder, ready to read, edit, or send.

3. Compare two versions of a file.

"Compare these two spreadsheets and tell me every row where the numbers don't match. Put the differences in a new sheet."

Cowork opens both files, lines them up, and finds the discrepancies. You get back: a difference report (or a new highlighted sheet) showing exactly what changed — the reconciliation done for you, ready to double-check.

Common mistakes and troubleshooting

A handful of avoidable gotchas account for most early frustration:

• Working without a Project. If Cowork seems to "forget" your context between tasks, you're probably running loose tasks instead of working inside a Project. Make the Project first — that's where memory and files live.
• Vague goals. "Help me with my files" gives Cowork nothing to aim at. Describe a concrete outcome: what you want, on which files, in what format.
• Wrong folder, or no folder. Cowork acts on what you point it at. If results look thin, check that the right files are in the Project folder and that you've actually referenced them.
• Approving without reading the plan. When it pauses before a consequential step, read the plan — that pause is your safety check, not a formality. Skim it before you say yes.
• Expecting it to touch everything. Cowork runs in a sandbox and won't reach into your external apps or online accounts on its own. It prepares the work; sending, posting, or syncing is yours to trigger.
• Starting too big. Handing over a high-stakes task on day one is the fastest way to lose trust. Begin small and let scope grow.

The habits that make it click

• Start small. Build trust with low-stakes tasks before handing over anything important.
• Give context generously. Cowork is only as good as what you tell it. Paste the real details.
• Keep one Project per area of work. Don't dump everything into one — separate Projects keep the memory and files relevant.
• Review every output that matters. Cowork collapses the busywork; it doesn't take responsibility. For client work, money, or compliance, you read and own the result.

That's the whole on-ramp. Get Pro, make a Project, delegate a small task, approve as you go — and let the scope grow as your trust does.

FAQ

How do I get access to Claude Cowork?

Claude Cowork is included on every Claude plan — even Free — with no separate purchase. Paid plans (Pro, about $20/month, and Max) add much higher usage limits and unlock plugin installs. Sign in at claude.ai, then open Claude Cowork on the desktop app.

Do I need to know how to code to use Claude Cowork?

No. Cowork is designed for non-developers. You work by describing what you want in plain English — 'organize this folder,' 'turn these notes into a report' — and Cowork does the steps, checking with you before anything consequential. There's no code to write.

What is a Cowork Project and why does it matter?

A Project is a workspace with its own folder, instructions, and memory. It's what lets Cowork remember your context across tasks instead of starting from scratch each time. Creating a Project first — before installing plugins or doing real work — is the single most important setup step, because anything that needs to persist (like a profile or saved files) lives in the Project's folder.

This article is educational. Claude Cowork outputs should be reviewed by a qualified human before professional use. Claude and Claude Cowork are products of Anthropic; The AI Career Lab is not affiliated with Anthropic.