Walk me through the Reason + Act cycle. Why is it better for complex, multi-step tasks than a single long prompt?

LLMs are notoriously bad at following "Write exactly 100 words." How would you design a workflow to strictly enforce a character or word limit?

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