--- id: giving-claude-context lang: en title: "Giving Claude context" seoTitle: "How to give Claude context" description: "How to give Claude context with uploads, profile instructions, and a short brief on how you work, so its answers fit your role, your world, and your style." part: getting-started-with-claude partTitle: "Getting started with Claude" partOrder: 2 order: 5 level: Beginner durationMinutes: 6 outcome: "Give Claude the right context so its answers fit your role, your work, and your style." summary: "Claude starts each chat knowing nothing about you. Give it context (uploads, profile instructions, a short brief) and its answers fit your role, work, and style." draft: false updated: "2026-07-26" furtherReading: - title: "Understanding Claude's personalization features" url: "https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features" note: "Profile instructions, project instructions, and styles, side by side." - title: "Upload files to Claude" url: "https://support.claude.com/en/articles/8241126-upload-files-to-claude" note: "What you can upload and the size limits." - title: "Create and manage projects" url: "https://support.claude.com/en/articles/9519177-how-can-i-create-and-manage-projects" note: "Keeping context together for ongoing work." - title: "What are skills?" url: "https://support.claude.com/en/articles/12512176-what-are-skills" note: "The next step up from a brief, covered in Part 4." keywords: - Claude context - custom instructions Claude - Claude file upload - Claude memory - how to give Claude context - profile instructions quiz: intro: "Five quick questions. Ace them all and you've finished Part 2." passScore: 5 questions: - q: "Why does giving Claude context matter so much?" options: - "It makes Claude type faster" - "By default Claude knows nothing about you, so context turns a generic answer into one that fits your work" - "It is only needed for coding" - "It changes the model you are using" answer: 1 explain: "Claude is capable but starts each chat knowing nothing about your role, your goals, or your style. Context is what closes that gap and makes the answer fit you." - q: "You want a rule, say your role and your preferred tone, to apply automatically to every chat. Where do you put it?" options: - "Retype it at the start of each chat" - "In your profile 'Instructions for Claude' in Settings" - "In a single artifact" - "Nowhere; Claude figures it out" answer: 1 explain: "Profile instructions are account-wide: set them once in Settings and they apply to all your conversations, until you change them. No need to repeat yourself." - q: "You have a big reference document you will feed Claude and reuse often. What is the leanest way to give it, and why does 'lean' matter?" options: - "A scanned PDF, because Claude likes images" - "A Markdown or plain-text version, because the context window is finite and text carries the least weight" - "A Word file with lots of styling" - "It never makes any difference" answer: 1 explain: "The context window is Claude's finite working memory for a chat. Plain text and Markdown carry the same words with almost no overhead, while a PDF is read as images and weighs far more. Lean material leaves more room for the actual work." - q: "What belongs in a short, reusable brief about your work?" options: - "Your account password" - "Who you are, your goal, your audience, your style, and any constraints" - "Nothing; briefs are a waste of time" - "Only your job title" answer: 1 explain: "A good brief answers who, what, and how: your role, what you are usually trying to do, who you write for, the tone you like, and what to avoid. A few lines is plenty." - q: "Before you paste context in, what should you keep in mind from the safety lesson?" options: - "Nothing; paste anything" - "Whether the material is something you're allowed to share on your plan" - "That longer is always better" - "That Claude cannot read files anyway" answer: 1 explain: "Context is powerful, but the safety rules still apply. On a personal plan, think before pasting sensitive or confidential material; the personal-versus-business divide from lesson 1.4 still holds." pass: badge: "Part 2 complete" title: "You know your way around Claude now." body: "Full marks, and that's Part 2 done. You can pick a plan, work the interface, choose a model, build artifacts, and feed Claude the context it needs. Next comes the big one: Part 3, prompting, where all of this turns into great results." retry: "Check the marked answers and give it another go. You've got this." --- > **Level:** Beginner ยท **Reading time:** ~6 min > > **What you'll be able to do:** give Claude the context it needs so its answers fit your role, your work, and your style. Here is the thing most people miss at the start: **Claude begins every chat knowing nothing about you.** Not your job, not your team, not who you are writing for, not the tone your company uses. It is like a brilliant new hire on day one, sharp as anything, but with zero idea how *your* world works. Context is how you brief that new hire. It is the single biggest lever on quality after prompting itself, and it is easy. Ask a cold Claude to "write a follow-up email" and you get something generic. Tell it *you are a logistics account manager, the client is annoyed about a late delivery, keep it warm but firm, three short paragraphs*, and you get something you could almost send. **Same request, night-and-day result, and the only thing that changed was the context.** ## Give it the material The most direct context is the stuff you already have. **Upload it.** Claude reads PDFs, Word documents, text files, spreadsheets (CSV and Excel), and images, up to 30 MB a file, using the **+** button in the message box. Point it at the actual report, the real spreadsheet, the brief you were sent, and it works from the source instead of your description of the source. This beats summarising from memory every time. If the answer depends on a document, **hand Claude the document.** Do not retype it, do not paraphrase it, do not hope Claude can guess. Give it the real thing and ask your question about it. **One tip on formats.** Claude reads all of these happily, but they are not equal in weight. A PDF is read as a set of *images*, and a Word file carries a lot of hidden styling, so both spend far more of Claude's memory than the plain words would. Text and **Markdown** (a simple plain-text format, see the glossary) carry the *same* words with almost none of that overhead. So when you control the format and the material is large or you will reuse it often, **prefer a `.md` or `.txt` file**: same information, a fraction of the weight, and cleaner for Claude to read. When you do not control it, upload the PDF or Word file anyway. Any source beats no source.
The same words, different weight An illustrative comparison of how much of Claude's memory the same content uses in different formats. Markdown or plain text is the lightest. A Word document is heavier because of styling. A PDF is the heaviest because each page is read as an image. The same words, different weight Markdown / .txt Lightest Word (.docx) Heavier: styling PDF Heaviest: read as images Illustrative. Prefer plain text or Markdown for large or reused reference material.
## Context isn't unlimited Why does the weight matter? Because Claude has a **context window**: the amount it can hold in mind in a single chat, its working memory. It is large, but it is *finite*, not bottomless. Everything counts against it: the files you add, the conversation so far, and the answer Claude is writing. Two things follow. First, **long chats and heavy files fill it up.** As a chat nears the limit, Claude quietly summarises the earlier parts to keep going, and in that summary some detail can slip. Second, **lean beats bloated.** A tidy Markdown brief and a focused chat leave more room for the real work than a stack of heavy PDFs and a conversation that has wandered for an hour. So the habits from earlier pay off here: **one topic per chat**, start fresh when you switch tasks (lesson 2.2), and feed Claude clean, lean material. The full mechanics, tokens, why long chats drift, and when to start over, open Part 4. For now, treat the context window as precious space and try not to waste it. ## Three places to put context Context can live at three levels, from "just for now" to "for good". Picking the right one saves you from repeating yourself.
Three places to put context Nested scopes. The widest is your profile instructions, which apply to every chat. Inside that, project instructions and files apply to every chat in a project. Inside that, anything you paste or upload applies to just the one chat. From "just for now" to "for good" Everything: profile instructions Set once in Settings. Applies to all chats, until you change it. This project: instructions + files Shared by every chat in the project. Great for ongoing work. This message: paste or upload Just this one chat. Quickest, most temporary. Widen the scope when you find yourself repeating the same context.
**This message.** Paste or upload context right where you need it. It lasts for the one chat. Perfect for a one-off ("here's the doc, summarise it"). **This project.** A **project** keeps files, instructions, and chats together for a piece of ongoing work, and its instructions apply to every chat inside it. Projects are open to everyone, free accounts included (up to five). This is the Part 4 topic; here, just know it exists for when a single chat is not enough. **Everything.** Your **profile instructions** (in Settings, under "Instructions for Claude") apply to *every* chat, automatically. This is where your durable facts live: your role, how you like answers, terms your industry uses. Set it once and stop repeating yourself. **The rule of thumb: the more often you'd retype something, the wider you should set it.** ## Write a short brief once The highest-value ten minutes you will spend is writing a **short brief about how you work**, then dropping it into your profile instructions (or a project). Keep it tight, a handful of lines. Answer who, what, and how.
What goes in a short brief Five lines for a good brief: who I am (role and team), my goal (what I usually want), audience (who I write for), style (tone, length, format I like), and watch-outs (what to avoid or any constraints). A brief that pays off, in five lines Who I am My role, my team, what I do day to day. My goal What I'm usually trying to get done. Audience Who reads my work: clients, my team, the board. Style Tone, length, and format I like. Watch-outs What to avoid, and any hard constraints.
That is all it takes. Something like: *"I'm a marketing lead at a mid-size logistics firm. I mostly write client updates and internal briefs. My readers are busy and non-technical. I like a warm, plain tone, short paragraphs, no jargon. Never invent figures; ask me if you're unsure."* Paste that once and every answer starts closer to right. **One caution, straight from the safety lesson:** context is powerful, but the rules still apply. On a personal plan, think before you paste anything sensitive or confidential. The personal-versus-business divide from lesson 1.4 has not gone away just because the context box is handy. ## Where this goes next Good context and good prompting are two halves of the same skill. **Context tells Claude who it's helping; the prompt tells it what to do.** Part 3 is all about the prompt. Later, in Part 4, that little brief grows up into projects and skills, reusable, shareable ways to give Claude context and behaviour on tap. For now, the habit is enough: never make Claude guess what it could simply be told. ## Try it Write your own brief, the five lines from the card above, about your real role. Keep it under a hundred words. Now open Settings and paste it into "Instructions for Claude". Then test it. Start a fresh chat and ask for something you actually need ("draft a short update to my team about this week"). Notice how much closer the first answer lands now that Claude knows who you are. That gap, between a cold Claude and a briefed one, is the whole point of this lesson. *(General exercise. Role and industry versions come once accounts are in.)* ## Key terms [Context](/glossary#context), [Context window](/glossary#context-window), [Custom instructions](/glossary#custom-instructions), [Markdown](/glossary#markdown), [Token](/glossary#token), [Project](/glossary#project)