Key principles for creating an effective prompt

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