The Course

Linguist

Learn to use AI well — when to think alongside it, when to hand it a task, and how to stay in control of both. No experience required.

Find your starting point →

Your starting point

You are not behind. You just haven't started yet.

Most people starting new jobs right now are in the same place — they've heard the word "AI" more times than they've actually used it deliberately. The first three modules will get you to a point where you can use AI for real work tasks before you've been in the job a week.

Start at B-01: Your First Message → Retake quiz

Your starting point

You've already started. Now find out why it's inconsistent.

Skip B-01 through B-03 — you know how to send a message and you've found your way around the platform. Start at B-04, which explains the single most common reason experienced users get unpredictable results: the way you phrase your request is directly shaping what comes back.

Start at B-04: Your Input Shapes the Output → Retake quiz

Your starting point

Skip ahead. Your foundation is already there.

The A-track is not a more advanced version of the chat interface tutorials you've already read. It's a different mode entirely — Claude Code runs in your terminal, reads your actual files, and can delegate discrete tasks to separate sessions. After this track you'll be able to control what tools it uses, write session briefs that produce evaluable outputs, and decide when delegation saves time versus when it just costs more.

Start at A-00: Getting Started with Claude Code → Retake quiz

Stage 1

Beginner 10 modules

Ten modules from your first message to a strong opening seed. No prior experience required.

↓

Your First Message

Send a message to an AI, read the response, and know that nothing broke.

Copy, Personalise, Use

Take any starting message, change the bracketed parts to match your situation, and send something that is actually yours.

Your Input Shapes the Output

See how the length and detail of your message directly affects the length and detail of the response.

One Thing at a Time

Send one task per message and get a focused, usable response instead of a scattered one.

Tell It When to Stop

Add a stopping condition to any message so the AI delivers exactly the amount you asked for.

What Just Happened?

Read an AI response, decide whether it answered what you asked, and know what to do next.

Recognise when a conversation has gone off track and restart it without losing your progress.

Your Two Projects

Set up persistent instructions so the AI remembers your preferences across every conversation.

Platform Orientation

Know where the main features are on your chosen AI platform so you can find them without searching.

The Opening Seed

Write an opening message that gives the AI everything it needs to get the task right the first time.

Stage 2

Enabled User 7 modules

Seven modules that sharpen your verb choice, context loading, and recovery skills — building on the Beginner foundation.

↓

The First Word Matters

Choose a verb that matches what you actually want, and predict how much the AI will decide on its own.

Tell It What to Leave Alone

Add constraints to any message so the AI stays inside the lines you set.

Context Is Fuel

Identify what context a task actually needs and load it before the AI starts.

Restate, Don't Patch

Recognise correction spiral signals and know when to rewrite rather than add.

Get the Plan First

Ask the AI to plan before it produces, and review the plan before it acts.

Migration and Re-seed

Recognise when a conversation is done and carry only what matters into the next one.

Your Reference Card

Build a personal one-page reference for everything you have learned.

Stage 3

Advanced Practitioner 10 modules

Ten modules for working with Claude Code: cost awareness, session hygiene, context management, tool selection, and agent delegation.

↓

This track requires Claude Code, Anthropic's command-line tool. See A-00 for setup.

Getting Started with Claude Code

Install Claude Code, send your first command, and understand what makes it different from the chat interface.

Mental Model Refresher

Understand what Claude Code is actually doing when it reads your project and responds.

Cost, Tokens, and What Things Actually Cost

Build a mental model of Claude Code costs so you can make deliberate spend decisions.

Write a CLAUDE.md file that gives Claude Code standing instructions for your project.

Context Awareness and Compaction

Understand what compaction does to your session and how to work with it.

Session Hygiene

Start every Claude Code session in a known state and keep context costs under control.

Output Engineering

Control the format, length, and structure of Claude Code's responses.

Name the right tool for a given task and guide Claude Code away from expensive tools when cheaper ones will do.

Agent Delegation and Briefing

Decide when to delegate a task to a subagent and write a 5-part brief that gives it everything it needs.

Capstone: A Real Project

Apply the full Advanced Practitioner toolkit to a real piece of work you need to do.