Before you begin
From install to ready.
Claude no longer stops at telling you how. Hand it a task in any conversation and it does the work: reading real files, writing real documents, finishing multi-step jobs while you do something else. This guide covers the initial setup, from a fresh install to an account that knows you and your work. Plan for about an hour.
What you'll have by the end
- Claude installed and configured on your Mac or Windows PC
- Global instructions that make Claude work the way you work
- An about-me memory system Claude reads at the start of every session
- Connected tools: Gmail, Calendar, Drive and more
- The essential skills switched on, and a folder structure that scales
- One official plugin installed and briefed on your business
- Guardrails set, so Claude proposes and you approve
What you need
| Requirement | Detail |
|---|---|
| A paid Claude plan | Pro or higher. Handing Claude tasks and letting it work in your folders aren't included on the free plan. |
| A computer | Mac (macOS 11 or later) or Windows PC (Windows 10 or later). Linux (beta): Ubuntu 22.04 or Debian 12 and later, x64 or arm64; this guide covers Mac and Windows. |
| About an hour | No code, no terminal. If you can install an app and type a sentence, you can do this. |
One mindset shift before you start. Treat Claude less like a tool and more like a capable colleague who uses your tools: files, inbox, calendar. The setup below is what you'd give any new team member: context on who you are, rules for how you work, and access to what they need. Nothing more.
This is the setup hour. Putting the setup to work (your first agent, scheduled tasks, real spreadsheets and decks) is what our hands-on course, Claude Essentials, covers; the last tab tells you how to go further. The course assumes this hour is done, and if you arrive without it, its first block walks the folder, the memory files and the standing brief again at speed. And if you'd like the broader orientation first, our free Getting Started with Claude guide covers the whole landscape: the web app, prompting, and where tasks fit.
A note on accuracy: menus, models and prices move fast. Everything here was verified against Anthropic's official documentation and a live account on the date in the footer. Where the app in front of you disagrees with this page, trust the app.
Step 1
Set up your workspace.
Install the app, pick a plan, find your way around, and give Claude one folder to work in.
1.1 · Get the app
No Claude account yet? Create one free at claude.ai first; the plan comes in 1.2. You can hand Claude tasks on the web there too, with nothing to install, and it's a fine way to try it. Install the desktop app for the full setup in this guide: it's what lets Claude work in folders on your computer.
- Download Go to claude.com/download and choose the macOS build. One universal app covers Apple Silicon and Intel; it needs macOS 11 (Big Sur) or later.
- Install Open the downloaded
.dmgand drag Claude into Applications. - Sign in Launch Claude from Applications and sign in with your Claude account.
- Download Go to claude.com/download and choose the Windows build. It needs Windows 10 or later. On an ARM-based PC (Snapdragon Surfaces and similar), check the download page for current support before you start.
- Install Run the downloaded installer. Use an account with administrator rights: a non-admin install still runs chat, but desktop tasks won't be available.
- Sign in Launch Claude from the Start menu and sign in with your Claude account.
1.2 · Choose your plan
| Plan | Price | Tasks? | Best for |
|---|---|---|---|
| Free | $0 | Not included | Trying Claude chat (Sonnet and Haiku only) |
| Pro | $20/mo, or $17/mo billed yearly ($200 up front) | Included | Almost everyone; every step in this guide works on Pro |
| Max 5× / 20× | From $100/mo, now with $100–200/mo in API credits | Included, more headroom | Handing Claude long tasks or running Claude Code all day |
| Team | $25 Standard · $125 Premium per seat ($20 / $100 billed yearly) | Included; an admin controls access | Teams that want one bill, shared settings and admin controls |
| Enterprise | $20/seat + usage at API rates (annual) | Included; an admin controls access | Large organizations with IT and compliance needs |
1.3 · Open Claude
- Start a conversation There's no separate mode to switch on. Open a new conversation and describe the outcome you want; Claude decides whether it's a quick answer or a longer job to run as a task. That's home for the rest of this guide. (Claude Code is a different tool, built for developers; you won't need it here.)
- Find the two controls Around the message box you'll find a control for choosing a project or folder, which you'll use in 1.4, and the permission setting, Manual or Auto, for how freely Claude acts.
- Keep Claude asking first Leave the permission setting on Manual, the default: Claude asks before it acts. Keep it there while you learn. (On Team and Enterprise, an admin decides whether Auto is offered at all. In every mode, Claude asks before permanently deleting files.)
1.4 · Create your workspace folder
- Make the folder In your Documents folder, create a new folder called
Claude Workspace. The same path works on Mac and Windows. - Connect it In the desktop app, pick the folder for a task with the folder control by the message box and allow access. To keep it as a project instead, go to Projects, click + and choose Use an existing folder. Settings lists the folders you've granted under Trusted folders, and shows where Claude saves its work under Storage folder.
Treat this folder as the desk you share with Claude. Everything you want Claude to reach goes inside; everything you don't, stays outside. That one habit does more for safety than any setting.
1.5 · Pick your model
The chip in the message box shows the model and the effort level (ours read Opus 5.5 · Medium); click it to change either. Start where it opens: Anthropic's own advice is that most work starts on Opus 5.5 at its default effort. For a complex, multi-step job, raise Effort (how long Claude thinks before acting) before you switch models. Drop to Sonnet 5.5 when speed matters more than depth on everyday work, or to Haiku 5.5 for the fastest replies, though at its lowest effort Haiku may skip a search it should have run.
Step 2
Write your global instructions.
Ten minutes here improves every session after it. Global instructions are the standing brief Claude reads before anything else: who you are, how to work with you, and where the lines are.
- Copy the brief into a chat Copy the Cortexa starting brief below and paste it into a new chat. Claude asks for each {PLACEHOLDER} you haven't filled, then hands back the finished brief.
- Answer in plain language Skip anything that doesn't fit how you work and Claude drops the line. Copy the completed brief it returns.
- Open global instructions Click your name or initials (bottom-left), choose Settings, and under General find Instructions for Claude. (If your account still shows the Chat | Cowork switch, the box is under Settings → Cowork → Global instructions; click Edit.)
- Save Paste the finished brief into the box and save it.
You're helping me finish my global instructions for Claude.
Below is my starting brief. Ask me for each {PLACEHOLDER} that is
still unfilled, a couple at a time, in plain language. If I say a
line doesn't fit, drop it. When everything is answered, give me the
finished brief as one copyable block, no placeholders and no
commentary, ready to paste into my global instructions in
Settings.
---
# Who you're working with
My name is {FULL NAME}; call me {PREFERRED NAME}.
Role: {JOB TITLE} at {COMPANY OR TEAM}.
In one sentence, my work: {WHAT YOU DO AND FOR WHOM}.
The people my work serves: {CLIENTS OR AUDIENCE — who they are and
what they count on you for}.
My priorities right now:
- {PRIORITY 1 — name the outcome, not the task}
- {PRIORITY 2}
- {PRIORITY 3}
# How to work with me
- Answer first, context after. Don't repeat my question back to me.
- Plain language. If a term needs explaining, choose a plainer term.
- Give me the one thing I asked for. Offer extras in a single line,
not as a second deliverable.
- If my request is vague, ask one clarifying question, then commit
to your best reading of it.
- Write in prose in conversation. Use headers, bullets and tables
when the content genuinely needs them.
- Preferred format for written work: {MARKDOWN / PLAIN TEXT / DOC}.
- Unless I say otherwise, write for {WHO USUALLY READS YOUR WORK}.
# Candor
- Tell me what's real. If a plan has a flaw, say so before I act on
it, not after.
- Disagree when you have a reason. I'd rather be corrected than
flattered.
- Skip compliments about my questions or ideas; grade the ideas
instead. Strong, workable or weak, and why.
- When you present options, rank them and name your pick.
- Separate fact from estimate. Label your guesses and say what would
confirm them.
- If something won't work, lead with that, then offer the closest
thing that would.
# Guardrails
- Confirm with me before anything hard to undo: sending, publishing,
deleting, sharing outside this workspace, or spending money.
- Anything outbound (email, messages, posts) stays a draft until I
send it myself.
- Client material is confidential. Never carry one client's files,
data or voice into another client's work.
- Client-facing work gets my review before it ships. No exceptions.
- Cite real sources or say you don't have one. Never invent
references, numbers or quotes.
- On legal, medical or financial questions, give me your read, then
flag what a professional should confirm.
# When in doubt
1. Candid beats comfortable.
2. Plain beats polished.
3. Short beats long, unless I asked for depth.
4. Ask once, then act.
5. Finish the work before describing the work.
Step 3
Build your about-me memory system.
What Claude remembers from your chats now reaches tasks that run in the cloud, but tasks working in your computer's folders still start fresh. (Memory is on by default on Free, Pro and Max; on Team and Enterprise it stays off for each member until they turn it on in Settings → Memory.) Three small files close that gap and add a record you own: per-project notes that live in your folder, where you can read, edit and move them. They're what separates a set-up Claude from a blank one.
The three files
| File | Purpose |
|---|---|
about-me.md | Who you are, your business, projects and audience: day-one context for a new team member |
writing-rules.md | How you want Claude to write, including what to avoid so it doesn't sound like AI |
memory.md | A running log Claude updates as you work, so projects pick up where they left off |
You don't write these by hand. Paste the prompt below into a new conversation with your workspace folder connected, and let Claude interview you and build all three.
Create an "about-me" folder in this workspace with three files you'll read at the start of every session: 1. about-me.md — my name, role, business, the tools I use, the people my work serves, and my current projects. Write it as the briefing you'd want on day one of a new job. 2. writing-rules.md — rules for writing as me. Start from Wikipedia's "Signs of AI writing" guide and distill it into a short list of what to avoid, plus anything you notice about how I write. 3. memory.md — a running project log. Append new entries at the bottom, update old ones in place, and keep a short list of open loops so nothing drops between sessions. Interview me for whatever you're missing, then build all three. When you're done, draft an updated global-instructions block that has you read these files at the start of every session, so I can paste it into my Settings.
- Answer its questions Claude will ask about your work before writing. The more specific your answers, the better every future session gets.
- Update your settings Paste the instructions block Claude drafts into your global instructions, in the same place you used in Step 2.
Before we start anything: how are you set up to work with me?
If the answer mentions your three files, the system is live. Every session from now on starts already knowing you.
This is the part of the setup that compounds. Ten minutes of instructions improve every session equally; the memory files get better every session, because Claude keeps adding to them. A month in, memory.md knows which arguments landed with which client and which drafts died on the vine, and you stop paying the re-explaining tax at the start of every conversation.
Step 4
Connect your tools.
Connectors are what turn Claude from a smart assistant into a colleague inside your actual workspace: your inbox, your calendar, your documents.
4.1 · Add your connectors
Open Customize in the left sidebar (it gathers connectors, skills and plugins in one place) and add connectors in this order. The + in the message box has a Connectors menu too, for switching them on and off as you work.
| Priority | Connectors | Why |
|---|---|---|
| Essential | Gmail · Google Calendar · Google Drive | Inbox, schedule and documents are where Claude pays for itself first |
| Recommended | Notion · Slack | If your notes or your team live there, Claude should be able to look things up. Local-file note apps (Obsidian, Logseq) need no connector; see 4.5 |
| Later | Anything else in your stack | Add tools when a real workflow needs them, not before |
4.2 · Decide on the training setting
In Settings → Privacy, review the Help improve Claude option. Left on, your sessions can be used to improve Anthropic's models and are kept, de-identified, for up to five years; switched off, they aren't used, and the standard retention period applies. The setting applies to Free, Pro and Max accounts, so set it deliberately, the way you and, if relevant, your clients would expect. Team and Enterprise accounts fall under Anthropic's commercial terms, and their content isn't used for training.
4.3 · Test the connection
Quick connector check: look at tomorrow on my calendar and at today's unread email, and tell me the three things that matter most. Flag anything you couldn't reach.
4.4 · Set the draft-only email rule
The Gmail connector can now send, reply and forward. Every connector has a permission setting: Always allow, Needs approval or Blocked. Make sure Gmail is on Needs approval, and before Claude touches your inbox in earnest, add one standing rule on top of that: it drafts, you send.
Standing rule for email: anything you write goes to my Drafts folder for review. You never send. Record this in memory.md so it holds in every future session.
4.5 · Optional: map a large workspace
Skip this on day one: Claude explores your folders and connected apps on its own. Later, if your folder or Notion grows large (or your notes live in a deep Obsidian vault, Google Drive or SharePoint), a one-off map saves Claude from searching the whole thing every time it needs one corner of it.
A note for Obsidian, Logseq and similar local-file note apps: they need no connector at all. Your vault is an ordinary folder of Markdown files, so connect it the same way you connected the workspace folder in Step 1, and Claude can read it directly.
Go through my {NOTION WORKSPACE / OBSIDIAN VAULT / GOOGLE DRIVE /
OTHER} and build a map of it: the key databases or folders, the
active projects, and where reference material lives. If I left that
placeholder unfilled, ask me where my notes live before you start.
Save the map as my-workspace-map.md in the about-me folder, and
note in memory.md to check the map before searching from scratch.
4.6 · Optional: Claude in your browser
The Claude in Chrome extension lets Claude browse sites, fill forms and click through workflows in your own browser (available on every paid plan since late August 2026). It's genuinely useful and genuinely powerful, which is exactly why we suggest adding it after the basics feel comfortable, not on day one.
Step 5
Switch on skills and shape the workspace.
Skills are packaged abilities: producing a formatted Word document, a working spreadsheet, a slide deck. Setup here means switching on the right ones and giving the workspace a structure that scales. Learning to build your own is course material, not setup.
5.1 · Enable the essentials
- Check Skill Creator Open Settings → Capabilities → Skills and make sure Skill Creator is switched on. It's the skill that helps Claude build other skills, and the course leans on it heavily later.
- Open the directory Go to Customize in the left sidebar, open Skills, click + and choose Browse skills. The + in the message box has the same Skills menu, with Manage skills and Browse skills.
- Add what you'll use Click Add on the document, spreadsheet and presentation skills that match your actual work; installed skills are on by default. Skip the rest, since adding one later takes seconds.
5.2 · Build the folder structure
Set up the rest of this workspace: 1. A "projects" folder. Each active project gets its own subfolder containing a brief.md (what the project is and what done looks like) and its own memory.md. 2. An "outputs" folder. Everything you produce lands here, in a subfolder per project, so I always know where finished work is. The about-me folder stays as it is. If I bring you something new and you're not sure whether it's a project, ask. Then record this structure in memory.md so it holds.
Claude Workspace/
├── about-me/
│ ├── about-me.md
│ ├── writing-rules.md
│ ├── memory.md
│ └── my-workspace-map.md (optional, from 4.5)
├── projects/
│ └── [project-name]/
│ ├── brief.md
│ └── memory.md
└── outputs/
└── [project-name]/
└── [finished work]
The shape matters more than the names: context in one place, live projects in another, finished work in a third. Claude keeps it tidy because the memory file now tells it to.
It earns its keep three ways. A brief and a memory file per project mean work resumes mid-thought instead of being re-briefed: pick a project back up after two weeks and Claude already knows where it stood and what's still open. Keeping each client in their own folder is the guardrail from Step 2 made physical, so one client's material can't drift into another client's work. And an outputs folder means finished work is never “somewhere in the chat”: it's a file, in a place you chose, ready to send.
Step 6
One plugin, and a look ahead.
Two last pieces round out the setup: install a single official plugin so Claude has a specialist on call, and get the lay of the land on scheduled tasks before the course puts them to work.
6.1 · Install one official plugin
If a skill is a tool in Claude's toolbox, a plugin is a specialist who arrives with their own toolbox: methods, checklists and knowledge for a whole domain. One is plenty for now, and Anthropic's own are the safe pick.
- Browse the directory Go to Customize, open the Plugins tab and look at what's available.
- Pick the official one that fits Claude for Small Business covers finance, sales and marketing workflows; the Claude for Legal practice-area plugins cover contract triage and meeting prep. Choose whichever maps to your actual role.
- Brief it A specialist who knows your business beats a generic one. Paste the prompt below into a new session after installing.
You now have the {PLUGIN NAME} plugin. (If that placeholder is
still unfilled, ask me which plugin I installed first.) Read my
about-me files, then tell me: which three of its workflows would
help my work most, and what would you need from me to run the
first one? Record the answer in memory.md.
6.2 · Scheduled tasks, at a glance
Scheduled tasks are the same idea as everything above, on a cadence: one standing brief that runs daily or weekly without being asked twice. They run in Anthropic's cloud, so they don't need your computer awake or the desktop app open. When you're ready, typing /schedule in any task starts one, and Scheduled in the left sidebar lists them all.
Safety & trust
Should you really let AI touch your stuff?
Fair question, and the honest answer is: only with the guardrails on. The good news is you just built most of them. Claude proposes; you approve.
Your safety net, layer by layer
- Folder scope Claude reaches only the folders you've connected. The shared-desk habit from Step 1 is the foundation everything else stands on.
- Manual permissions With the permission setting by the message box on Manual, the default, Claude checks with you before it acts. Move to Auto only once you know how it works; in every mode, Claude still asks before permanently deleting files.
- Standing rules Your starting brief requires confirmation before anything hard to reverse: sending, publishing, deleting, spending.
- Draft-only email The Gmail connector can send, so in Step 4 you kept it on Needs approval. Your standing rule adds a second lock: messages stay in your drafts folder until you send them yourself.
- The training setting On a personal plan, you chose in Step 4 whether your sessions may help improve Anthropic's models. Team and Enterprise content isn't used for training.
- Connector permissions Each connector can be set to Always allow, Needs approval or Blocked, and you connected the minimum. What isn't connected can't be read.
- Computer use If you later enable computer use, review which apps Claude may operate before you rely on it. Keep it away from anything you'd hesitate to hand a contractor.
Working with regulated or genuinely sensitive data? That's a conversation with your compliance team before it's a task for Claude. On Enterprise, cloud tasks are captured by the Compliance API, while tasks run on your own computer keep their history on that machine, where admins can't manage it centrally. Ask your admin what's recorded before assuming the trail exists.
Wrap-up
The checklist, and where to go next.
Copy the checklist into your task manager and tick through it. If every box is checked, your setup is done.
# Claude setup checklist ## Step 1 — Workspace - [ ] Claude Desktop installed (Mac: drag to Applications · Windows: run installer as admin) - [ ] Windows only: Virtual Machine Platform enabled, then restarted - [ ] Paid plan active (Pro or higher, for tasks and local folders) - [ ] Permission setting left on Manual (the default) while you learn - [ ] Workspace folder created and connected (Documents/Claude Workspace) - [ ] Model and effort checked (start where it opens; raise effort before switching models) ## Step 2 — Global instructions - [ ] Starting brief filled in and saved in Settings ## Step 3 — About-me memory system - [ ] about-me.md created - [ ] writing-rules.md created - [ ] memory.md created - [ ] Global instructions reference all three files ## Step 4 — Connectors - [ ] Gmail connected, draft-only rule recorded - [ ] Calendar connected - [ ] Drive connected - [ ] Workspace map built (optional, once your folder or notes grow large) - [ ] Training setting reviewed (Settings → Privacy; personal plans) - [ ] Claude in Chrome installed (optional, later) ## Step 5 — Skills & folders - [ ] Skill Creator on, plus the document/spreadsheet/deck skills you'll use - [ ] Folder structure built (about-me / projects / outputs) ## Step 6 — Extras - [ ] One official plugin installed and briefed - [ ] Read the scheduled-tasks overview (the build itself comes with the course)
Six habits that compound
- Dictate long prompts instead of typing them: built-in dictation on the Mac, Win+H on Windows, or a tool like Wispr Flow.
- Once your starting brief is solid, leave it alone. Day-to-day changes belong in the about-me files.
- A map helps once a workspace is big: Claude goes straight to the right place instead of searching the whole thing. Until then, let it explore.
- When you discover a better workflow, tell Claude to record it in memory.md. That's how the setup keeps getting better.
- Watch the progress panel on early runs. You'll learn how Claude thinks, and catch wrong turns while they're cheap.
- Start where the chat opens; raise Effort for hard jobs before switching models; Sonnet or Haiku when speed matters more than depth.
Specific in, specific out. The quality of everything above tracks the quality of your about-me files: vague context produces vague work, from AI and from colleagues alike. If writing the first ask is the hard part, our free Prompt Generator matches you three ready-to-run Claude workflows in a couple of minutes.
Go further: Claude Essentials
This guide ends where the interesting part begins. Your account now knows you, reaches your tools and keeps its memory; what it hasn't done yet is real work. That's the ground Claude Essentials covers: Cortexa Academy's hands-on course where you build your first agent, put jobs on a schedule that runs while you sleep, and turn real files into spreadsheets, decks and dashboards, with the patterns worth stealing along the way. Intelligence, applied.