The questions students ask most

For normal use, no.

• Your Claude Pro or Max plan covers three surfaces: Claude.ai Chat, Cowork and Claude Code.
• An API key is only for a standalone webapp or tool that calls the Anthropic API directly. It is billed separately, per token.
• No web page can sign in to your personal plan.

Your plan has usage limits that reset over time, so waiting a while usually clears it.

Very long single sessions can also drift and get worse. If answers start going sideways, close the conversation and start a fresh one.

It only reads what you point it at, nothing else on your computer.

As a habit, never paste passwords, keys, or other secrets into a chat.

Your work is not gone. A Cowork project is a link to a folder on your computer; the app lost the link, not the folder. Your files are exactly where they were.

The fix takes thirty seconds: open Cowork, create a new project, choose Use a Folder, and point it at the same folder. Everything comes back.

Two habits prevent the panic: keep your working folders in OneDrive or iCloud so the files follow you between machines, and remember the tell: a Cowork project is tied to this computer, a Chat project lives in your account and follows you anywhere. The full picture is in Where are you working?

Start on Pro. It is plenty for learning and everyday work.

Move up to Max only if you keep hitting limits or you run heavy, long workloads regularly.

No. That is the whole point. You describe what you want in plain English and the AI does the building.

Treat it like a confident new hire: check important answers against a real source, and ask it to cite where its claim comes from.

For anything that matters, add a reviewer step. See /loops/ for how, and the receipts for the evidence that it works.

Tokens are the small chunks of text the AI reads and writes. The context window is how much it can hold in mind at once.

The rest of the core terms live on the Leverage Ladder.