Why are delimiters like ###, """, or <xml> tags important in long prompts? How do they help prevent the model from getting confused between instructions and data?

How does asking the model to "Respond as a panel of three experts (a coder, a security lead, and a PM)" differ from asking it to "Respond as a Senior Engineer"?

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?

We know "think step-by-step" works. But when should you not use Chain of Thought (CoT) in a production app?