Skip to main content
Back to Library
Prompt Engineering Guide

Mastering Summarize document
on Claude 3.5 Sonnet

Stop guessing. See how professional prompt engineering transforms Claude 3.5 Sonnet's output for specific technical tasks.

The "Vibe" Prompt

"Summarize the following document: {document}"
Low specificity, inconsistent output

Optimized Version

STABLE
{document} [INST]Task: Summarize the provided document. To achieve a comprehensive, concise, and accurate summary, follow these steps: 1. **Analyze and Deconstruct**: Read the document thoroughly to identify the core subject, main arguments, key facts, and conclusions. Pay attention to the document's structure (e.g., introduction, body paragraphs, conclusion) and any headings or subheadings. 2. **Identify Key Information**: Extract the most important sentences, phrases, or data points that directly contribute to the main message. Discard extraneous details, examples, or repetitive information. 3. **Synthesize and Condense**: Combine the identified key information into coherent sentences and paragraphs. Rephrase complex ideas in simpler terms where possible, ensuring accuracy and preserving the original meaning. 4. **Draft Summary**: Write a preliminary summary, ensuring it flows logically and covers all essential aspects identified in step 2. 5. **Review and Refine**: Check the summary for: * **Accuracy**: Does it truly reflect the document's content? * **Conciseness**: Is it free of unnecessary words or repetition? (Target 1-3 paragraphs, max 250 words, unless document length necessitates more). * **Clarity**: Is it easy to understand? * **Completeness**: Does it include all critical information? * **Objectivity**: Does it avoid adding new interpretations or opinions? 6. **Final Output**: Present the refined summary. Ensure it is self-contained and provides a clear understanding of the original document's content without requiring the reader to consult the original. Once you have completed these steps, provide ONLY the final summary as your output. [/INST]
Structured, task-focused, reduced hallucinations

Engineering Rationale

The optimized prompt leverages chain-of-thought by breaking down the 'summarize' task into a series of explicit, sequential steps. This guides the model through the cognitive process required for an effective summary, minimizing ambiguity and encouraging a structured approach. It explicitly instructs the model on what to 'think' about (e.g., identifying core subject, extracting key info, synthesizing) and what characteristics the final output should possess (accuracy, conciseness, clarity, objectivity). The 'vibe_prompt' is too simplistic, offering no guidance on how to perform the summarization, often leading to less comprehensive or less focused outputs.

0%
Token Efficiency Gain
The optimized prompt explicitly defines 'summarize' through a step-by-step process.
The optimized prompt specifies desired characteristics of the summary (e.g., accuracy, conciseness, objectivity).
The optimized prompt uses structured formatting (numbered steps, bolding) to improve clarity for the AI.

Ready to stop burning tokens?

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

Optimize My Prompts