Tutorials
Every tutorial is free and stands on its own — pick the one you need, work through it at your own pace, and your progress is saved automatically.
start a conversation with Claude and read its reply with a critical eye.
Before you prompt, you can describe what a good answer looks like — which makes everything after it easier.
tell the difference between a vague prompt and a precise one — and write the precise kind on purpose.
give Claude the background it needs to give you an answer that actually fits your situation.
shape Claude's reply — its length, format, and tone — just by asking for it directly.
use an unsatisfying reply as the raw material for a better follow-up — instead of starting over or giving up.
explain in one sentence why Claude sometimes states false things with complete confidence.
run a 3-step verification check on any factual answer Claude gives you.
pull honest criticism out of a model that's built to be agreeable.
By the end, you'll have found one real failure mode in Claude yourself, by deliberately hunting for it.
By the end, you'll understand why Claude in a browser can't touch your files — and you'll have Claude Code installed in your terminal, ready to read, write, and run things on your own machine.
By the end, you'll have used Claude Code to turn a plain-language description of a small program into working code you ran yourself.
You can tell a demo from a tool, and you know exactly where the real work begins.
You can write a small set of gold-standard examples that pin down exactly what a correct output is — your standard, made concrete and checkable.
You can measure how often your tool is right, find the pattern in its mistakes, fix the right thing, and prove the fix worked.
You can package a working tool so someone else — or future you — can run it, trust it, and keep it alive, and you understand why that last part is the whole point.
You can decide, for any task, how much to let AI do on its own — and you understand why "more automated" isn't always "better."
You can tell which tasks are worth the effort of building a reliable AI workflow, and which aren't.
How it works
Claude.ai is free, with no install. Tutorials 1–10 run entirely in your browser — we walk you through opening it in the first one.
Each one stands on its own — short, focused, and outcome-based. Start with #1 if you're new, or jump straight to whatever you need.
Every tutorial includes something to actually do — a prompt to run, a comparison to make, a step to take in your own conversation with Claude.
Tutorials 11–16 carry what you learned into Claude Code — installing it, building something of your own, then making it reliable enough to trust.