A primer

Starting with Claude.

The landscape, the concepts worth knowing, and a prompt you can paste to set up your own context.

Most people who try Claude and bounce off it don't have a bad tool — they have a blank context. Claude doesn't know who you are, what you work on, or how you like to be talked to. Every conversation starts from scratch. Twenty minutes of setup changes this, and this primer walks you through it.

· · ·

The landscape, briefly

There are so many terms… Claude Chat, Code, Cowork, MCPs, connectors, skills, plugins, CLAUDE.md. Most explainers make these sound more complicated than they are. Here’s the map, grouped by when to touch each piece. Start at the beginning, and reach for the “when you’re ready” items as concrete needs arise. Everything else can wait until you have a specific reason to use it.

01
Start hereThe essentials. Set these up first.

Claude (the chat app)

Where almost everyone should start.

claude.ai or the mobile app. Conversations, file uploads, artifacts, web search, connectors to things like Gmail and Notion. If you’re learning Claude, don’t jump to anything else yet.

User preferences

The single highest-ROI thing most people never set up.

A block of text in your settings that tells Claude who you are and how you want to be talked to. Applied to every new conversation. This is what this primer is mostly about.

02
When you’re readyTurn to these once you have ongoing work.

Projects

A way to group related conversations and share context.

Each project has its own instructions and can hold reference files. Useful once you have an ongoing body of work — a book, a client, a class, a long-running idea.

Connectors (MCP)

Permissions that let Claude reach into your other tools.

Gmail, Google Drive, Notion, Slack, GitHub. The “MCP” acronym you’ll see everywhere is just the behind-the-scenes protocol. Add connectors one at a time when you have a specific need, not preemptively.

03
LaterWorth knowing about, not worth setting up yet.

Claude Code

A terminal tool for developers. Skip unless you write code.

Lives in your terminal, works on your actual files, can run tests and make commits. Powerful, but irrelevant unless you’re doing technical work in a real repo. If you’re not sure whether you need it, you don’t.

Cowork

A desktop tool that does multi-step tasks on your computer.

Think of it as Claude with hands — it can operate on files, manage documents, and run workflows. Still maturing. Evaluate it when you have a real recurring task you want automated, not before.

Skills

Reusable playbooks Claude loads automatically when relevant.

“Here’s how my team writes case studies.” “Here’s how I format client reports.” Worth building when you catch yourself explaining the same process more than twice. Most people don’t need these for months.

CLAUDE.md

A text file that gives Claude persistent project context.

Specifically for Claude Code. Lives in a code repository. Ignore unless you’re a developer.

· · ·

Why user preferences matter more than people think

User preferences are the closest thing Claude has to “knowing you.” They do two things:

01

They give the tool context about who you are

What you do, what projects you’re juggling, what vocabulary is natural for you, what you’re trying to learn. Without this, the tool defaults to an imagined average user, or basically nobody. And you are not nobody.

02

They tell the tool how to respond to you

Length, tone, formality. Whether to push back on your ideas or just execute. Whether to ask clarifying questions before diving in. How to handle uncertainty. A lot of AI frustration stems from answers in the wrong lane. They aren’t bad responses, but they aren’t what you need.

A useful way to split them: contextual preferences (who you are) and behavioral preferences (how you want the tool to respond). The starter prompt at the bottom of this page covers both.

· · ·

A real example, annotated

Here's a condensed version of what a mature set of preferences looks like — from someone who uses Claude across several unrelated areas of work. Don't copy this. Your life is different. But it's useful to see the shape of something that works before you build your own.

Excerpt — a real user's preferences

Workstreams & Context

I work across several distinct, usually unrelated areas. Treat each conversation's context as set by me — don't carry assumptions across workstreams unless I explicitly invite it.

— Client work (strategy and BD)
— Board work with a nonprofit community
— A climate-focused nonprofit where I sit on the board
— A class I'm taking on AI and climate

Why this exists: she context-switches constantly across unrelated domains. Without this, Claude would bleed assumptions from one into another — for example, using her work tone when she's writing to her community. If your work is mostly one thing, you may not need this section at all.

Before executing, confirm intent

If my request is ambiguous, ask a clarifying question first. I'd rather refine my request than rework a full response.

Why this exists: she'd rather spend 30 seconds clarifying than 20 minutes reading an answer aimed at the wrong problem. This single line changes most interactions — without it, Claude defaults to guessing.

Honesty over agreeableness

I prefer honest and direct over agreeable. Don't soften bad news or overvalidate. Push back especially on strategic assumptions, underestimating complexity, and solving the wrong problem.

Why this exists: AI tools default to sycophancy. Without a line like this, you get affirming mush. This is probably the single most valuable behavioral preference you can write.

Work modes

Calibrate to the mode I signal: Brainstorming — poke holes. Stress-testing — balanced analysis. Drafting — I've decided; help me execute.

Why this exists: the same request (“help me with this proposal”) needs very different responses depending on whether she's still thinking or already committed. Naming the modes gives her a shorthand to switch registers without re-explaining each time.

Notice what's not here: no lists of favorite colors, no hobbies, no life story. Preferences that don't change how the tool responds to you are noise. Keep it lean.

· · ·

Your starter prompt

Rather than giving you a template to fill in — which is where most people bounce — the prompt below runs the interview for you. Paste it into a new conversation. The AI will ask you a series of focused questions, one at a time, then draft your preferences for you to edit.

You can come back and revise later. Your first version won't be your last. The goal is to stop starting from scratch.

I want your help setting up my user preferences in Claude — the profile that shapes how you respond to me across all our conversations. I haven't written one before, so I'd like you to interview me rather than handing me a blank template. Before we start, here's what I know about user preferences: - They apply to every new conversation I have with you. - They work best when they reflect my actual work and how I want to be communicated with — not aspirational versions of either. - There's a difference between CONTEXTUAL preferences (who I am, what I work on) and BEHAVIORAL preferences (how I want you to respond — tone, length, when to push back, when to ask before acting). Here's how I'd like you to run this: 1. Ask me about my work first. What I actually do day to day, the distinct areas I spend time on, and which ones are likely to come up in our conversations. If I do very different things (e.g., a day job + a side project + a creative pursuit), help me name them as separate workstreams so you can keep context clean. 2. Then ask about how I want to be communicated with. Length, tone, formality, whether I want you to push back on me or just execute, how you should handle uncertainty, whether I want clarifying questions before you dive in, etc. Give me concrete options rather than open-ended questions where possible — I'll learn what's available by choosing. 3. Ask whether there are things I want you to be careful about. Sensitive topics, confidentiality expectations, things I don't want you to assume about me. 4. At the end, draft my user preferences as a single block I can paste into my Claude settings. Keep it concise. Flag anything where you think I might want to reconsider later as I learn what works. Ask me one focused question at a time. Don't batch them. If my answer is vague, ask a follow-up before moving on. I'd rather this take 10 minutes and produce something I'll actually use than 2 minutes and produce generic scaffolding. Start with question one.
After the interview

Claude will output a block of text. Go to your Claude settings — in the web app, click your initials bottom-left, then Settings → Profile — and paste it into the “What personal preferences should Claude consider in responses?” field. Save. You're done. Every new conversation will now start with Claude knowing who you are.