Basics
Give Claude the context it needs, write clearer prompts, and choose the right model.
Getting started
Tell Claude what it can't look up, describe the result you want, add a role when it helps, and check it understood before it starts.
4 techniques →-
What Context Does Claude Need From You? Claude needs what it can't look up: who the result is for, what has already happened, and what the result has to achieve. Level 1: Basic promptsClaude may have itdon't retype these
- Memory from earlier chats
- Project knowledge files
- Web search, if it's on
Only you can sayput these in the prompt- Who the result is for
- What already happened
- What it has to achieve
-
How Do You Check Claude Understood Before It Starts? Ask Claude to restate the task and list its assumptions, then tell it to stop until you reply. Level 1: Basic prompts
- 1Ask: restate, then stopinclude your assumptions
- 2Claude restates and waits
- 3You correct one lineread the out-of-scope items first
Repeat until it's right, then say go -
How Do You Tell Claude the Result You Want? Describe the finished thing, who will use it, and how you'll judge it. Level 1: Basic prompts
- Topica rejection email
- Taskwrite a rejection email
- Resultshe applies again next year
- Result you can checktwo short paragraphs, the real reason, no empty promises
-
Should You Give Claude a Role, and Where Does It Go? Yes, when you want a particular tone or focus, and one sentence is enough. Level 1: Basic prompts
- 1Your messagethis chat only
- 2Project instructionsevery chat in that project
- 3Instructions for Claudeall your chats
- 4API system promptrequests from your app
Prompt basics
Learn where instructions go in a long prompt, how many examples to show, how to set a format, and why to say what to do rather than what to avoid.
4 techniques →-
Where Do Instructions Go in a Long Claude Prompt? Put long documents at the top and your instructions and question at the bottom. Level 1: Basic prompts
- 1The documentsin tags, at the top
- 2Examples, if you have thembelow the documents
- 3Instructions and your questionat the end
-
How Many Examples Should You Show Claude? One real example is a good start, and it's often enough to fix a format. Level 1: Basic prompts
- No exampleyou describe it, Claude guesses
- One exampleoften fixes a format, can teach the wrong traits
- Two that differshows what is allowed to vary
- 3 to 5, variedwhat Anthropic's docs recommend
-
How Do You Get Claude to Answer in a Set Format? Name the format exactly: columns, number of items, length, and what goes before and after it. Level 1: Basic promptsClaude can driftAPI enforces it
- "Use JSON"
- Named fields
- XML-tagged sections
- Structured outputs
-
Why Tell Claude What to Do Instead of What to Avoid? Because a ban rules out one thing and leaves everything else open. Level 1: Basic promptsDo
- "Flowing paragraphs of prose"
- Describe the result you want
- Give a reason for any real ban
Don't- "No markdown" on its own
- Leave the target open
- Ban something without saying why
Models & limits
Choose between Fable, Opus, Sonnet and Haiku, and learn how much fits in a chat, what Claude can't know, and when to start a new one.
4 techniques →-
What Can't Claude Know, and How Do You Fill the Gap? Claude's built-in knowledge stops at a cutoff, and Anthropic lists June 2026 as the reliable knowledge cutoff for Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5. Level 1: Basic prompts
- June 2026Reliable knowledge cutoff
- November 2026About five months laterthis stretch needs search or you
-
How Much Can You Fit in a Claude Chat? On paid plans, chats with Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5 have a 1M-token context window, and some older models have 500K or 200K. Level 2: Context
- 1System prompt, instructions, toolsconnectors take a lot
- 2Files and text you addedthe part you control
- 3Conversation so fargrows every turn
- 4Claude's reply and thinkingneeds room too
- Which Claude Model Should You Use? Claude comes in four models: Fable, Opus, Sonnet and Haiku. Level 1: Basic prompts
-
When Should You Start a New Claude Chat? Start a new chat when the topic changes, when Claude keeps returning to ideas you dropped, or when you're close to a usage limit. Level 1: Basic promptshow off track the chat is →New chat, handoff notename what you rejectedNew chatcarry nothing overKeep goingClaude can summarize older messagesNew chata short summary at mosthow far the topic has moved →
Do you know the Claude basics?
Six questions on context, models, examples and what Claude can't know. You'll see the reason after each answer, with no account required.
What this module teaches
Three things decide most of what you get from Claude: what you put in the prompt, how you arrange it, and how much of its limits you use. The lessons cover those in that order. Each card has a prompt you can paste now and steps to try in the app. Start with Getting started if you're new, or go straight to Models and limits if you keep running out of usage.
What has changed recently
Some advice you'll find online is out of date. Memory is now on by default on Free, Pro, Max and Ultra, so a new chat doesn't always start from nothing. Current models have a 1M-token window in paid chats, and Claude can summarize older messages to keep a long chat going. Anthropic's docs also recommend putting long documents above your question, which is the reverse of what many guides say.
How do I start using Claude?
Go to claude.ai or open the app, and describe what you need, who it's for and how you'll judge it. The Free plan includes Sonnet and Haiku. You don't need any special syntax, and a plain, specific request works well.
Is Claude free to use?
Yes, there's a Free plan with Sonnet and Haiku and up to five projects, and it doesn't include Opus, Fable or Claude Code. Paid individual plans were $20, $100 and $200 a month when checked on 4 November 2026.
Does Claude remember my earlier chats?
Often, yes. Memory is on by default on Free, Pro, Max and Ultra, and paid plans can also search past chats. You can review memory at Settings, Your Claude, or turn it off for one chat from the + menu before your first message.
Which Claude model should a beginner use?
Start with Sonnet for everyday work. Move up to Opus or Fable only when you can see the answer falling short, and use Haiku for simple tasks you repeat many times.