Prompting Tips
Mastering the art of AI prompting can transform your interactions with language models, enabling you to obtain more precise, useful, and creative responses. This page outlines practical frameworks, strategies, and examples to help you craft effective prompts across various applications. Whether you're a beginner or an experienced user, these prompting techniques will enhance your ability to communicate with AI and leverage its capabilities to their fullest potential.
RACEF Prompting Framework
Definition
[role] Act as a world-class copywriter.
[action] Write a one-line description of my business that I can use on my website.
[context] I run a social media marketing agency for real estate agents, specifically focusing on TikTok and Instagram.
[examples] One example I like is “Software that keeps you running while you keep the world running"
[format] Give it to me in a short list with no other explanation
Example:
Knowledge Base
What is Retrieval-Augmented Generation?
Retrieval-augmented generation (RAG) is optimizing the output of a large language model so it references an authoritative knowledge base outside of its training data sources before generating a response.
Example: Claude Projects
Advanced Prompting
- Prompt Engineering - Develop Out Sections
Example:
- Step Prompting - Step Prompting is a way to break big tasks into smaller steps. You give one instruction at a time, and the AI completes each step before moving on to the next.
- Branch Prompting - Custom GPTs
- Chain Prompting
