Principles of Well-Defined Prompts

Explore innovative techniques like chain-of-thought, active-prompt, and reason and act, while remaining aware of potential pitfalls and limitations.

Previously, we saw how important prompt designing and engineering are when controlling models’ output. Here are some best practices we can use to improve our prompts, as well as some practices we should avoid:

  • Clarity: Use simple sentences and instructions that can easily be understood by ChatGPT.

  • Conciseness: Favor short prompts and short sentences. This can be achieved by chunking the instructions into smaller sentences with clear intentions.

  • Focus: Keep the focus of the prompt on a well-defined topic so that there is no risk of output being too generic.

  • Consistency: Maintain a consistent tone and language during the conversation so that coherent conversation can be ensured.

  • The “Act as...” trick: The hack of letting ChatGPT act as someone or something has proven to be extremely powerful. We can shorten the context we have to provide to the model by simply asking him to act like the person or system we want information from. We’ve already seen the interview-candidate example, where ChatGPT acted as an interviewer for a data scientist position. A very interesting prompt is that of asking ChatGPT to act as a console. Here is an example of it:

Get hands-on with 1200+ tech skills courses.