If you need a structured response (like a JSON object), would you rather use a "System Prompt instruction" or the model's native "Function/Tool Calling" capability? Why?

In an API inference call, what is the functional difference between the System, User, and Assistant roles?

Your "v2" prompt works better for Question A but worse for Question B. How do you manage prompt versions in a codebase?

How do you prevent a user from using your "Search Tool" to look up internal sensitive data they shouldn't have access to?