Unlock ChatGPT's Power: 3 Rules to Master AI Prompts

Greg Schwartz, a freelance prompt engineer, shares three key rules for writing effective prompts for AI chatbots like ChatGPT:

  1. Give the chatbot a role: Tell the chatbot what kind of persona it should adopt, such as "writer," "party planner," or "programmer."
  2. Provide plenty of context: Give the chatbot specific instructions and background information about the task you want it to complete.
  3. Break complex tasks into multiple prompts: For intricate tasks, provide step-by-step instructions in separate prompts.


  • Schwartz transitioned from UX design to prompt engineering in 2023. He now helps clients improve their prompts for large language models like ChatGPT.
  • Clear and specific prompts are crucial for generating good results. Schwartz emphasizes three key principles:
    • Role definition: Specify the chatbot's role or persona to guide its response.
    • Context: Provide ample background information and instructions for the task.
    • Step-by-step prompting: Break down complex tasks into multiple prompts for better understanding.
  • An example is given: A client wanted ChatGPT to turn a document into a memo, but without clear instructions, the output was poor. Specifying the memo's length and structure would improve the outcome.
  • Another example demonstrates breaking down tasks: To identify the most mentioned US locations in an article, provide separate prompts to:
    • List all mentioned locations and their frequencies.
    • Filter for locations in the US.
    • Sort by frequency and select the top three.


Related post


Unlock AI's Magic: Master the Art of Prompt Engineering

Prompt engineering is the art of crafting precise queries to get the most accurate, relevant, and useful responses from AI models like GPT-3 and GPT-4. What is Prompt Engineering? Examples of prompts: Best practices for writing prompts: Things to avoid: Prompt engineering is a valuable skill for maximizing the potential…

GraphRAG: Unlocks LLM Potential for Analyzing "Secret" Data

GraphRAG, a novel approach developed by Microsoft Research, significantly improves the ability of Large Language Models (LLMs) to analyze and answer questions about unseen data (private datasets). This is achieved by using LLMs to create knowledge graphs from the data, which are then leveraged to enhance the retrieval and generation…