Key principles for creating an effective prompt

1. Introduction

The way we ask a question directly affects the answer we receive. This is equally true when working with artificial intelligence (AI) tools and systems. They cannot determine what we want unless we formulate our requests clearly and precisely. Users often receive unclear, incomplete, or overly general answers because their queries are too broad or insufficiently specific.

By mastering the skill of properly formulating queries, you will be able to:

• Obtain accurate and relevant information.

• Save time.

• Understand and process information more easily.

• Use technology more effectively in teaching and research.

Regardless of the sophistication of artificial intelligence tools, the quality of their answers depends largely on how we formulate the query – known as the prompt.

Questions to consider

• To what extent does the way we put questions (prompts) to artificial intelligence differ from how we put questions to humans?

• What are the key differences, and what do they mean for our communication with technology?

• How would you adjust your question to get the best possible answer in both cases?

2. How do artificial intelligence tools and systems "understand" queries?

When you ask an AI tool – whether it is a conversational system or an image-generating tool – a query (called a prompt), it does not interpret it as a human would. These systems do not possess consciousness, thought, or understanding in the human sense. Instead, they use advanced mathematical models and statistical patterns to identify what you are seeking and generate the response that best matches your query.

Here is how it works:

• Converting to numbers

  • The first step is to convert your query – whether text, image, or sound – into a series of numbers. This is how a computer “translates” information into its own language.
  • If the input is text, it is broken down into smaller units (words or parts of words), each assigned a numerical value that reflects its meaning and its relationship to other words.
  • If it is an image, the data is converted into numbers that describe the characteristics of its pixels.

• Finding patterns and connections

         Once all information is expressed as numbers, the AI tool begins its analysis. It uses the extensive “knowledge” acquired during training on billions of examples.

• • Recognising relationships: The model identifies how different parts of your query relate to each other. For example, in the phrase “a dog that flies,” it understands that the verb “flies” describes the noun “dog.”

  • Focusing on the essential: Like a reader searching for the main idea of a text, the system determines which words or parts of the query are most important and focuses on them.

  • Comparison with learned patterns: Your query is compared to what the model has “learned” during training on large data sets. The model does not remember individual examples but generalises patterns, language structure, facts, and ways to connect information.

• Generating answers

         Based on this analysis, the AI tool predicts the most likely or appropriate answer to your query.

• • For text queries: The model predicts the next most likely word, then the next, gradually building the entire answer.

  • For visual queries: It gradually “draws” an image from numerical data, pixel by pixel, creating a representation that matches the description in the query.

Artificial intelligence tools do not think or understand the world like humans. Their strength lies in recognising complex patterns and making statistical predictions. This is why they can create extremely convincing and useful answers – thanks to sophisticated data processing and the ability to recognise connections that humans have enabled during the learning process.

What is prompt engineering?

Prompt engineering is the skill and process of designing effective queries for artificial intelligence tools.

It is a new form of digital literacy that involves understanding how artificial intelligence systems “think” and respond to different formulations of requests.

The goal of prompt engineering is to maximise the capabilities of artificial intelligence through clearly defined, contextually precise, and purposefully structured queries. In practice, this means the user carefully chooses:

• Role – from which perspective the tool should respond

• Task – what exactly needs to be done

• Format – in which format the result should be displayed

• Restrictions – rules, tone, or response limits

Example of a prompt:

“You are a math teacher. Prepare a short lesson plan on linear equations for third-year high school students. Display the plan in a table and use simple, clear language.”

This approach allows users to precisely direct the work of artificial intelligence, increase the relevance of responses, and develop awareness of how digital tools process information.

In education, prompt engineering is becoming an important skill for teachers and students, as it enables the conscious and responsible use of artificial intelligence in learning, research, and content creation.

Creating different types of content (e.g., text, visual, or audio) often requires different artificial intelligence tools and different query design strategies. In other words, how we formulate a prompt depends on what we want to produce: text, image, sound, or multimedia.

Specific rules and approaches apply to each type of content.

Here is what to pay attention to for certain types of prompts:

Textual content – requires a clearly defined tone, goal, and structure. It is important to determine the intended audience, the style (e.g., formal, popular, educational), and the specific content required (e.g., summary, explanation, comparison).

Visual content – requires precise descriptions of image elements, style, composition, and mood. The general rule is: the more detailed the description, the more precise the result.

Audio and audiovisual content – includes additional dimensions such as tone of voice, rhythm, emotion, or atmosphere, making queries more complex.

Multimodal content – combines text, image, and sound, and requires carefully coordinated instructions for the tool to properly integrate all components.

Understanding these differences helps users choose the appropriate AI tools and methods of interaction, thereby increasing the accuracy, creativity, and efficiency of the results.

Additionally, for those seeking a deeper understanding of prompt engineering strategies and techniques when working with large language models, the Prompt Engineering Guide developed by OpenAI is recommended.
The guide provides examples, practical advice, and advanced approaches to query design to improve the quality and consistency of generative model responses.

Note: The presented query design model (Role–Task–Format–Restrictions) is based on pedagogical guidelines for developing digital and AI literacy used by various university guides, such as those from the Australian Catholic University (ACU) (2024). Although not formalised as a theoretical model in the scientific literature, this approach serves as a practical framework for training users in effective communication with AI tools.

Image source: Shutterstock

3. Precision and clarity of the prompt

When communicating with artificial intelligence (AI) tools, the way we formulate a prompt plays a key role. A prompt is an instruction, question, or request that the user sends to the AI system to generate an answer, create content, or perform a specific action. In other words, a prompt is the input that guides the AI system and shapes the quality of the results generated.

Why are precision and clarity important?

As in human communication, unclear or overly general instructions can lead to incorrect or superficial answers.

If the query is not clear enough, the AI can misunderstand the context, omit important information, or provide an incomplete result.

Conversely, precisely and clearly formulated queries allow the tool to better understand what we are looking for and to generate content that is more relevant, structured, and useful.

Think of a query as a guide you give to a person:

• If the instructions are unclear, the result is likely to be incomplete.
• The same applies to AI – precision increases accuracy.

Tips for clear and precise query design:

• Use specific terms and avoid ambiguous words.

• Do not ask questions that are too broad.

• Be specific about the scope and context of what you are seeking.

• When possible, specify the desired format of the answer (e.g., “list,” “two sentences,” “with an example”).

Example:

When designing a query, avoid vague phrases like:

“Tell me about linear mathematics.”

Instead, use specific and focused wording, such as:

“Explain the basic concepts of linear algebra and give examples of their application.”

In this way, you direct the AI tool precisely toward the desired goal and increase the quality of the response you receive.

Precision and clarity are not just technical aspects but are also part of digital literacy, enabling more efficient and meaningful communication with AI. A clearly defined query is the foundation of good collaboration between the user and the tool – it determines the direction, tone, and level of complexity of the response the AI can provide.

This topic forms the basis of a broader skill known as prompt engineering – the thoughtful design of queries by which the user consciously influences the quality and relevance of the AI’s response.

4. Structuring requirements into small steps

When creating queries for AI tools, it is helpful to divide complex requirements into smaller, more understandable parts. This process is known as task decomposition.

Why is this important? 

Large, complex queries can often confuse AI systems, resulting in incomplete, superficial, or illogical answers.

By breaking your query into simpler steps, the model can better understand each part and gradually produce a more accurate and meaningful result.

How to do it?

• Instead of asking for everything at once, divide your query into smaller parts.

• First, request an explanation of the basic concepts.

• Next, ask for examples that clarify the context.

• Finally, request an application, comparison, or solution proposal.

Example:

Instead of a single query:

“Explain the theory, history, and applications of computer networks in education and create a lesson plan about it.”

It is better to ask a series of smaller, related questions:

• “Explain the basic concepts of computer networks.”
• “Give a brief history of the development of computer networks.”
• “How are computer networks used in education?”
• “Propose a lesson plan on computer networks for students.”

This approach increases the precision, clarity, and quality of the answers you receive and allows you to gradually build a more complex result based on accurate and verified parts.

Tip:

This technique is especially recommended in educational settings when using AI for lesson planning, creating teaching materials, or research analysis. It helps the model “think step by step” and reduces the possibility of error.

5. Provide additional context

Providing more information helps the AI tool better understand your needs and tailor its response to your goal. Context guides how the tool generates content and increases the likelihood that the result will be relevant, clear, and usable.

What can you include in context?

• Purpose – Why do you need the response (e.g., for teaching, a presentation, or research)?

• Audience – Who is the content intended for (students, teachers, or a professional audience)?

• Writing style – What tone and language do you want (e.g., professional, popular, concise, or informal)?

• Response format – What form do you want the result in (e.g., list, table, essay, or plan)?

Why is this important?

Without a clearly defined context, the AI may assume circumstances that do not match your expectations.

Context helps the system “understand” your intent and generate a response tailored to the situation, audience, and purpose.

Example:

“Write a summary of a scientific article on digital pedagogy, tailored to first-year students.”

In this example, the context includes the type of content (summary), the topic (digital pedagogy), and the audience (first-year students). With this information, the AI tool can create a response appropriate to the audience’s knowledge level and focused on the educational goal.

Tip: The more relevant information you include in your query, the more precisely the AI tool will “understand” what you need. A well-defined context does not limit the model’s creativity; on the contrary, it helps it be more focused and useful.

Questions to consider:

1. Can you recall a situation when you received an irrelevant response from an AI tool? What part of the context might have been missing?

2. How would you reframe your most frequently used query to include clearer context (purpose, audience, style, or form)?

6. “Chain-of-Thought” Technique

The term Chain-of-Thought (CoT) refers to an approach in which the artificial intelligence (AI) system is asked not only to provide a final answer, but also to explain how it arrived at that answer. In other words, the user includes in their query a request for the AI to work through its thought process in a series of logical, interconnected steps. This method of communication not only delivers information but also offers insight into the process – the "thinking" of the model – which results in deeper, more reasoned, and pedagogically useful answers.

AI systems often answer simple queries too briefly or superficially, providing ready-made conclusions without further explanation. However, if we ask them to outline their answer step by step, they are more likely to produce content that demonstrates the flow of analysis, cause-and-effect relationships, and logical reasoning. In education, this is especially valuable because it allows students to understand not only the result but also the path to the solution, encouraging reflection and the development of critical thinking.

How to Stimulate a Chain of Thought?

The key lies in how the question is formulated. Instead of asking for a simple answer, it is helpful to explicitly request an explanation of the reasoning process. This can be done with prompts such as:

“Explain your procedure step by step.”

“Analyse the problem, then propose solutions and justify their effectiveness.”

Example question:

“Explain how you would approach solving the problem of student motivation in online classes. First, list possible causes of low motivation, then suggest pedagogical interventions, and finally explain why these solutions might be effective.”

In this example, the instructor defines both the topic (student motivation) and the structure of the answer (causes → suggestions → justification).

This gives the model a clear framework and prompts it to generate a thoughtful, logically connected response that resembles an analytical essay.

Structure of an Answer That Follows a Chain of Thought

An answer obtained in this way usually includes several clearly separated parts:

• Problem identification – recognition of the key challenge
• Cause analysis – explanation of why the problem occurs
• Solution proposals – specific steps or strategies
• Efficacy justification – argument for why the proposed approaches could work in practice

Such a structure not only improves the quality of the answer but also makes it easier for the user to follow the train of thought and compare it with their own conclusions. In an educational context, this allows AI tools to be used as partners in the learning process – not just as sources of ready-made information, but as surrogates for dialogue and the exchange of ideas.

Application in Teaching

Teachers can use this technique in two ways. First, as a tool for planning and reflection, for example, when preparing lessons, analysing teaching problems, or designing assessment strategies. Second, as a teaching activity in which students learn how to think, argue, and evaluate solutions in a structured way.

Example of a student assignment:

“Ask an AI tool to explain a step-by-step solution to a pedagogical problem.

Then analyse each step: what would you keep, what would you change, and why?”

Such an activity develops self-assessment, critical thinking, and reasoned decision-making skills.

Pedagogical Significance

The chain of thought should not be seen as a technique that automatically increases the accuracy of answers, but as a didactic tool that gives the model structure and provides the user with insight into the logic of reasoning. Although AI can sometimes produce convincing but incorrect reasoning, this very fallibility makes it useful for educational purposes – it encourages discussion, comparison, and evaluation. In other words, a chain of thought is not a guarantee of truth, but an opportunity for learning through the thought process.

Reflection Questions

• Choose one challenge from your own teaching practice (e.g., student inactivity, late submission of assignments, or a decline in motivation).
• How would you formulate a query to an AI that would trigger a “chain of thought” – that is, analyse causes, suggest solutions, and explain their potential effectiveness?

Recommended source:

Learn Prompting (2024). Chain-of-Thought Prompting

7. Additional tips for more 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.

8. Conclusion

Creating effective queries is a skill that greatly contributes to the successful use of artificial intelligence and digital tools in education. Many artificial intelligence tools and systems allow users to create multimedia content (text, images, graphics, video, audio recordings, etc.).

Precision of expression, clarity of formulation, logical structuring of requests, adding context, and applying the Chain-of-Thought technique are key elements for obtaining relevant, understandable, and applicable information.

However, even the most advanced artificial intelligence systems cannot replace human knowledge, judgment, and experience. In higher education, it is especially important to emphasise that a quality query – or a good prompt – stems from a deep understanding of the content, pedagogical goals, and the context in which the tool is used. Artificial intelligence can analyse, synthesise, and propose solutions, but it does not understand the purpose of learning or the specific needs of students. For this reason, human expertise remains central in any application of artificial intelligence in teaching and research.

At the same time, it is necessary to maintain a critical attitude toward the results. Artificial intelligence systems can sometimes hallucinate – generating inaccurate, incomplete, or fabricated information that seems convincing. Therefore, it is essential to check facts, confirm sources, and thoughtfully evaluate the answers before applying them in teaching or research.

In other words, the effective use of artificial intelligence relies on a combination of human expertise, digital competence, and critical thinking. This combination allows technology to become a true ally in education – a tool that extends, but does not replace, human understanding and professional responsibility.

Questions for reflection:

• How do your professional knowledge, experience, and pedagogical judgment influence the quality of the queries you design for artificial intelligence tools? 
• Consider how understanding the topic, learning objectives, and students' needs shapes the way you ask questions and interpret answers.

Image source: Shutterstock

9. Literature