Prompt
The message in which you tell Claude what to do. The clearer it is (what, where, limits, how you check), the better the result.
How it appears in the course
The message you write to Claude is called a prompt.
When Claude repeats the same mistake, the conversation is already full of failed attempts. That’s why /clear with a better prompt helps more than one more correction.
The data brought in through MCP (web pages, tasks, emails) can contain hidden instructions, put there by someone else to trick Claude. This is called prompt injection. That’s why you shouldn’t give broad write permissions.
Where you learn it
In module 01 · How to talk to Claude, in the Claude Code for Beginners course.
Related terms
Learn Claude Code from zero, in plain English
12 modules with 1–2 minute lessons, which you can also do on your phone. The first two modules are free.