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

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

Instead of one giant 2,000-word prompt, why might you split a task into smaller, sequential prompts?

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