Claude · Module 01 of 8

Basics

Get set up and productive with Claude fast — the core mental model and first prompts.

3 lessons12 exercises
Topics & techniques

Getting started

Accounts, models, and your first useful prompt.

4 cards →
Knowledge card
Give Claude the Context It Can't Guess
A foundational habit of giving Claude the specifics of your situation it has no way to know — who the audience is, what happened before, the goal, the constraints — instead of a bare request stripped of context.
L1 · Basic prompts
Knowledge card
Have Claude Restate the Task in Its Own Words
A beginner move where, for anything non-trivial, you ask Claude to restate the task and its assumptions in its own words before it starts — so you can catch a misunderstanding while it's still free to fix.
L1 · Basic prompts
Best practice
Open With the Outcome You Want, Then the Details
A simple prompt structure for beginners: lead with the outcome you actually want — the finished thing and who it's for — then give constraints and context, and end with the specific ask. The goal comes first because everything else is in service of it.
L1 · Basic prompts
Knowledge card
Start by Telling Claude Who It Is and Who You Are
A reliable first-message shape for Claude: name the role you want it to take, give the context you're working in, state the constraints, then make the ask — in that order.
L1 · Basic prompts

Prompt basics

The anatomy of a prompt that gets a usable answer.

4 cards →
Knowledge card
Put the Instruction Before the Data
A prompt-structuring habit where you state the instruction first, then paste the long data — the document, code, or transcript — clearly separated below it, rather than burying the ask at the end of a wall of text.
L1 · Basic prompts
Best practice
Show Claude One Example of What Good Looks Like
Attaching a single concrete example of the output you want — the right format, tone, and depth — instead of describing it in the abstract.
L1 · Basic prompts
Knowledge card
Tell Claude the Format You Want Back
A core prompting habit of telling Claude the shape you want the answer in — a table, a bulleted list, JSON, a two-sentence summary, a specific set of headings — rather than leaving the format to chance and reworking it after.
L1 · Basic prompts
Knowledge card
Say What to Do, Not Just What to Avoid
A prompting habit of phrasing instructions as what you want Claude to do, not only what to avoid — 'write in plain, warm English' rather than 'don't be so formal and don't use jargon'.
L1 · Basic prompts

Models & limits

Pick the right Claude model and understand what it can and can't hold in mind.

4 cards →
Knowledge card
Know What Claude Can't Know
A clear mental model of the boundary between what Claude actually knows — general knowledge up to its training cutoff, plus whatever you give it — and what it cannot know: recent events, live data, and anything private to you or your organisation.
L1 · Basic prompts
Concept
Know What Actually Fits in the Context Window
A working understanding of the context window: the finite budget of tokens Claude can attend to at once, shared across the system prompt, everything you've pasted, the conversation history, and the space left for the reply. It is short-term working memory, not permanent storage.
L2 · Context engineering
Best practice
Match the Claude Model to the Task, Not the Hype
A habit of choosing the Claude model by what the task actually demands — a smaller, faster model for simple high-volume work, the most capable model for hard reasoning — rather than defaulting to the biggest one for everything or the cheapest one to save money.
L1 · Basic prompts
Knowledge card
Start a Fresh Chat When the Thread Drifts
Knowing when to abandon a long, meandering conversation and open a fresh one — carrying over only the context that still matters — instead of pushing on in a thread that has filled with stale or contradictory turns.
L1 · Basic prompts
Claude basics, explained

Tell Claude who it is and who you are

The fastest way to get good work out of Claude is to set the frame before the task. Give it a role and give it yours: 'You are a senior editor; I'm a founder writing to investors.' That single line changes the register, the assumptions, and the bar of the whole response. From there, start with the outcome you want rather than a list of steps — describe the destination and let Claude find the route. These two habits do more than any amount of prompt tinkering.

Match the model, and show an example

Claude comes in several sizes, and picking the right one matters: a fast model for quick edits and lookups, a deeper model for architecture, long documents, and hard reasoning. The other high-value habit is showing one concrete example of what 'good' looks like — a sample output anchors Claude far better than another paragraph of description. Knowing what fits in the context window, and what does not, rounds out the basics.

The basics topics to explore

This section covers getting started, prompt basics, and models and limits. Work through the cards below in order — each is a small, tested habit that compounds, rather than a block of theory.

Frequently asked
How do I start using Claude?

Open Claude, give it a role and tell it who you are, then start with the outcome you want rather than a list of steps. Showing one example of a good answer sharpens results immediately. The getting-started cards below walk through your first prompts.

How do I write a good Claude prompt?

Set the frame (Claude's role and yours), lead with the outcome you want, and include one example of what good looks like. Give it the relevant context rather than a vague description, and it will stay faithful to what you asked for.

Which Claude model should I use?

Use a fast model for quick edits, drafts, and lookups, and a deeper model for architecture, long-document reasoning, and hard problems where accuracy matters most. Matching the model to the task is a core basic skill.

What is a context window in Claude?

It is how much text — your prompt, the conversation, and any files — Claude can consider at once. Claude's window is large, which lets it reason over long documents, but filling it with irrelevant material still hurts, so include what matters.

Test yourself

Do you know the Claude basics?

Six questions on the fundamentals — framing a first prompt, knowing what Claude can't know, and picking the right model. No sign-up, instant score, and you can share how you did.

  1. Q1 You open a fresh chat and ask Claude to 'write a follow-up email'. Why does the answer come back generic?
  2. Q2 For a non-trivial task, what's the cheapest way to catch a misunderstanding before it costs you a full round trip?
  3. Q3 You're pasting a long document for Claude to work on. Where should the instruction go?
  4. Q4 You want output in a particular tone and shape. What beats describing it as 'concise and professional'?
  5. Q5 Which instruction is most likely to get you the tone you actually want?
  6. Q6 Which is the correct mental model of Claude's context window?
0 / 6 answered