DIEP Flap Surgery Recovery Prompts | TXDIEPFLAP

Prompting
1

Hi Team,

I have been using OpenAI models to understand and structure information related to medical recovery topics, specifically after undergoing DIEP flap surgery and breast reconstruction. I am trying to use prompting to get clear, structured, and consistent information for recovery tracking, care planning, and general understanding of post-surgical guidance.

However, I am noticing that when I ask similar questions in different ways, the AI responses sometimes vary significantly in depth and structure. In some cases, the response is very detailed, while in others it becomes too general or incomplete, even when the intent of the prompt is the same.

I am trying to understand how to improve prompt consistency for such sensitive and complex medical recovery topics.

  1. What are the best prompting techniques to ensure consistent and structured responses for medical recovery-related queries like post DIEP flap surgery care and breast reconstruction recovery?

  2. Are there recommended prompt patterns or system instructions that can help reduce variability in responses for health-related informational queries?

4

Welcome to the dev Community! @jerryshah

That’s a really valid concern, especially for something like post-surgical recovery where consistency actually matters.

This can happen because small changes in phrasing can shift how the model interprets intent, especially for complex domains like medical recovery.

A few things that usually help improve consistency:

  • Use a fixed structure in your prompt (e.g., “Always respond with sections: Overview, Timeline, Risks, Care Tips”)
  • Set expectations explicitly (e.g., “Be detailed, structured, and avoid generalizations”)
  • Provide a reference example of the exact format you want
  • Keep key constraints repeated across prompts instead of relying on prior context
  • Use system instructions to lock behavior (e.g., “You are a medical information assistant that provides structured recovery guidance in consistent sections”)

For sensitive topics like post-surgical care, it also helps to anchor the scope (e.g., “focus on general recovery patterns, not personalized medical advice”) so the model doesn’t shift tone or depth.

~Smith