The STAR technique is a method for structuring prompts that is comprised of four parts:
- Situation: Provide the context for the request. Describe the problem or task that needs to be addressed. This sets the stage for ChatGPT to understand the scenario.
Example: “Act as a Machine Learning Engineer.” - Task: Specify the specific role or objective within the situation. Clearly outline what needs to be accomplished or resolved. This helps ChatGPT understand the goal or purpose of the request. Provide any relevant information or constraints that ChatGPT should consider when generating a response.
Example: “I will write some machine learning concepts and it will be your job to explain them in easy-to-understand terms.” - Appearance: Define the structure of the Output. What should the result look like? Anticipate the desired outcome or what you hope to achieve by completing the task. This helps ChatGPT understand the criteria for success and tailor its response accordingly.
Example: “This could contain providing step-by-step instructions for building a model, demonstrating various techniques with visuals, or suggesting online resources for further study. My first suggestion request is <I have a dataset without labels. Which machine learning algorithm should I use?>” - Refine: Include any specific constraints or important details that are necessary for the output to meet your needs.
Example: “Use only english academic papers. No blogs.”
“[image]Without words. Without characters. White background. Widescreen image.”
Always create prompts taking these steps into account.