In a few-shot prompt (giving examples), does the order or diversity of the examples matter more for the model’s performance?

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?

How would you set up an experiment to prove that a new prompt version is actually 10% better than the old one? What metrics would you track?

In models that support it (like Claude), how does "pre-filling" the assistant's response (e.g., starting with {) help with structured output?