Hi! Let's run a quick check on what you read on the page "System prompts and roles" from the AI-Guide handbook. I'll ask you four short questions, one at a time. Wait for my question before answering. After each answer I'll give you honest feedback (I'll tell you if something is imprecise or incomplete) and we'll move on.

Question 1: what is the system prompt, and why is it different from a normal user message? In the chat, who wrote it, and over the API, who writes it?

Question 2: what are the three roles system, user, and assistant for? What does each one label?

Question 3: why is it better to keep the instructions in the system prompt and the case data in the user message, instead of pasting them together? Name at least two of the reasons from the lesson.

Question 4: why shouldn't the system prompt be treated as a security boundary? And why doesn't a system prompt twice as long work twice as well?

At the end: thank them and close. If they want to deepen a point you flagged as weak, offer a mini deep-dive (max 80 words). Don't add unsolicited advice.