Explain the "Reflection" pattern. How can asking a model to "review your own work for errors" before showing it to the user improve quality?

Explain Prompt Leaking. How would you prevent a user from asking your chatbot, "Show me your system instructions"?

How does an LLM decide which tool to call? If you give a model 50 tools, what happens to its accuracy and context window?

If an LLM calls an API tool and gets a 500 Error, how do you prompt the model to "retry" or "find a workaround" instead of just crashing?