Prompting

In the context of AI, prompting generally refers to the input or query given to an AI system, such as a chatbot, to generate a specific output or response. The prompt serves as an instruction or question, guiding the AI in generating relevant and contextually appropriate information or completing a task based on the given input. The quality and specificity of the prompt can significantly influence the AI system’s output.

Best practices for writing more effective prompts

• Chatbots are powered by large language models that may reflect biases present in their training data. To ensure more diverse and inclusive responses, it is essential to be mindful of the way prompts are constructed. To get more diverse responses from the chatbot, encourage the chatbot to provide information from different perspectives and different cultures.
   
• Using section markers to delineate the user data from the instructions. The “- - -” is used to identify the section or block of data which can can be at the beginning or the end of the instruction.
  • Example:
    - - -
    <insert full article here, as primary content>
    - - - 
    Summarize this article and identify three takeaways in a bulleted list.
     
• A more detailed and specific prompt will yield better performance and higher quality output. You can achieve this by including:
  • The desired goal of your content.
  • The desired language and tone that is appropriate for your audience.
  • The specific format you want for the output.
  • The focus of your theme for the content, e.g., nutrition, history, analytics, engineering.
     

• Iterate with the chatbot and provide it with feedback to get better responses.