Skip to main content
Back to Library
Prompt Engineering Guide

Mastering Creative writing
on Llama 3.1 70B

Stop guessing. See how professional prompt engineering transforms Llama 3.1 70B's output for specific technical tasks.

The "Vibe" Prompt

"Write a story about a dragon who lost his fire and has to adapt to a new life."
Low specificity, inconsistent output

Optimized Version

STABLE
You are a seasoned fantasy novelist with a flair for emotional depth and character-driven plots. Your task is to write a short story (500-700 words) about a dragon who has lost his fire. This is not a story about regaining fire, but about the profound emotional and practical adaptations he must make to a new, fireless existence. Focus on: 1. **Character Introduction (50-75 words):** Introduce 'Ignis,' a once-proud, fire-breathing dragon, highlighting his former glory and the moment he realized his fire was gone. Use evocative language. 2. **Initial Despair and Isolation (100-150 words):** Describe Ignis's immediate emotional response to his loss. How does it impact his identity? His interactions with other creatures? Show, don't just tell, his struggle. 3. **A Forced Adaptation/Discovery (150-200 words):** Detail a specific challenge he faces due to his lack of fire (e.g., cooking, defense, warmth, crafting). How does he creatively overcome it using other senses or abilities? Introduce a small, unexpected discovery or skill he develops. 4. **A Moment of Acceptance/New Purpose (150-200 words):** Show Ignis finding a new, fireless way to contribute to his environment or community, or a new meaning in his life. End on a note of quiet resilience or unexpected contentment, rather than longing for his past. Constraint Checklist: - Focus on adaptation, not regaining fire. - Word count: 500-700 words. - Evocative language used. - Character's emotional journey is central. - Ends on a note of acceptance/new purpose. Critique Awaited: After generating the story, you will be asked to identify a core theme and suggest one area for further development.
Structured, task-focused, reduced hallucinations

Engineering Rationale

The optimized prompt works by employing several advanced prompt engineering techniques. First, it establishes a clear 'persona' for the AI ('seasoned fantasy novelist'), which guides the tone and style. Second, it breaks down the complex creative task into smaller, manageable, and logically sequenced steps using a 'Chain-of-Thought' approach (Character Introduction, Despair, Adaptation, Acceptance). Each step has specific word count guidelines, ensuring structural balance. Third, it provides clear 'constraints' and 'focus areas' (e.g., 'not about regaining fire,' 'show, don't tell'), preventing the AI from deviating and ensuring the core request is met. Finally, the 'Critique Awaited' section primes the AI for further interaction and encourages a deeper analysis of its own output, leading to potentially more coherent and thoughtfully crafted initial responses. This level of detail significantly reduces ambiguity and increases the likelihood of a high-quality, on-topic creative output.

0%
Token Efficiency Gain
The generated story adheres to the 500-700 word count.
The story focuses on Ignis's adaptation to life without fire, not on regaining it.
The narrative successfully follows the four outlined structural points (introduction, despair, adaptation, acceptance).

Ready to stop burning tokens?

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

Optimize My Prompts