Key principles for creating an effective prompt

Check your results

• The answer you receive from an AI tool is not necessarily definitive. If the first answer is not precise enough, lacks depth, or does not address your needs, consider reformulating your query. Instead of accepting the first result as is, clearly indicate what you want changed. For example:

  • “Give more concrete examples from higher education.”
  • “Explain more concisely and in simpler language for first-year students.”

Use examples in your query to clarify exactly what you want and make your requirements easier to understand.

• It is very helpful to show the model precisely what you expect. By including an example of the desired tone, level of detail, or structure in your query, you increase the likelihood of receiving an answer that is immediately usable.

• For example:

  • Instead of simply saying: “Write a lesson plan on digital literacy”, it is better to say: “Write a lesson plan on digital literacy for a first-year undergraduate. Include learning outcomes, class activities, and a suggested independent work assignment.”

    This way, you are not asking for just any plan, but for a format that meets your specific teaching needs.

Limit the scope of the prompt

• Avoid overly long prompts that include too much information at once, as this can confuse the AI and reduce response quality.
• Do not ask for too many different things in a single prompt. Such queries often result in answers that are superficial and inconsistent in style. It is better to break down complex requests into several smaller steps. Instead of asking for the subject's history, problem analysis, solutions, and pedagogical plan all at once, ask in stages. This helps the model remain focused and precise in each part.

Be willing to experiment

• It often takes several attempts and different formulations to achieve the best possible result.

• Working with AI is a process, not a one-time query. It often requires multiple attempts, reformulations, and additional clarifications to obtain a result that is truly useful for your teaching or research.

  Practically, the “ask – evaluate – refine – ask again” approach is much more effective than simply asking once and copying the answer.