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

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?

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

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