Skip to main content
Back to Library
Prompt Engineering Guide

Mastering Medical report summary
on Mistral Large 2

Stop guessing. See how professional prompt engineering transforms Mistral Large 2's output for specific technical tasks.

The "Vibe" Prompt

"Summarize this medical report in a way that is easy to understand for a general audience. Highlight the most important information."
Low specificity, inconsistent output

Optimized Version

STABLE
As a highly skilled medical summarizer, your task is to synthesize the provided medical report into a concise and easily digestible summary for a non-medical professional. Prioritize clarity and accuracy. Follow these steps: 1. **Patient Information:** Extract and present the patient's age, gender, and relevant demographic details. (If not present, state 'Not available'). 2. **Chief Complaint(s):** Identify and list the primary reason(s) for the patient's visit or medical concern. 3. **Key Diagnoses:** Enumerate all confirmed diagnoses from the report. 4. **Significant Findings:** Describe the most critical objective findings (e.g., lab results, imaging interpretations, physical exam findings) that support the diagnoses or indicate severity. 5. **Treatment Plan/Recommendations:** Detail the proposed or ongoing treatments, medications, procedures, and follow-up instructions. 6. **Prognosis/Outlook (if available):** Briefly state the expected course or outcome of the condition. Structure the summary with clear headings corresponding to these steps. DO NOT include medical jargon without immediate, simple explanations. Maintain a neutral, empathetic tone. Focus on actionable information and key health aspects.
Structured, task-focused, reduced hallucinations

Engineering Rationale

The optimized prompt leverages chain-of-thought by breaking down the complex task into sequential, manageable steps. It explicitly defines the persona ('highly skilled medical summarizer'), target audience ('non-medical professional'), and desired output format (clear headings, no jargon). This structure guides the model to systematically extract and present information, leading to a more accurate, comprehensive, and user-friendly summary. The negative constraints ('DO NOT include medical jargon') further refine the output. By pre-defining the structure, it reduces the model's need to infer the best approach, making it more efficient and consistent.

0%
Token Efficiency Gain
The summary correctly identifies the patient's chief complaint(s).
All key diagnoses are accurately extracted and presented.
The summary avoids complex medical jargon or explains it clearly.

Ready to stop burning tokens?

Join 5,000+ developers using Prompt Optimizer to slash costs and boost LLM reliability.

Optimize My Prompts