Education resources › Blog › 7 approaches to using AI in the classroom (with prompts)

7 approaches to using AI in the classroom (with prompts)

7 approaches to using AI in the classroom (with prompts)

4 min read
  • Phones & technology

In only a few short months since the explosion of ChatGPT, it feels that Artificial Intelligence (AI) has become the hot topic in education. It potentially offers exciting and innovative ways to aid learning and empower students – but also potential for misuse.Interestingly, a lot of research is currently being carried out to help guide effective application of AI in education, with one recent paper identifying seven potential approaches. So, let’s see what the researchers suggest…

We are seeing a lot of research come out on how AI can be used as a learning tool – with even more still to come.

However, one (very) recent paper caught our eye. In it, researchers offer seven specific approaches to utilising AI in the classroom by getting it to play a specific role in the learning journey. They even provide colour-coded prompts for each, explaining how to assign the AI:

  • A role and goal
  • Step-by-step instructions
  • Pedagogy
  • Constraints
  • Personalisation

Let’s look at each of these approaches in more detail…

1. Using AI as a mentor: Providing feedback

    Feedback is an invaluable tool for growth. However, providing constructive criticism in a way that is both helpful and motivating to each student can be challenging. This requires a personalised approach that may be time consuming.

    AI can help automate certain aspects of feedback, such as grammar and spelling suggestions. By offering immediate and adaptive responses to projects, assignments and assessments, AI can also analyse individual learning patterns and offer tailored recommendations.

    2. Using AI as a tutor: Providing direct instruction

    Offering individualised attention and one-on-one support can be difficult in your classroom. This research suggests that AI can play a significant role in acting as a tutor for your students.

    With the ability to analyse vast amounts of data rapidly, AI platforms can identify students’ strengths and weaknesses to tailor lessons and activities accordingly. They can also recommend supplementary materials, such as articles, videos or practice exercises based on students’ interests and performance. This approach can help students grasp concepts effectively, encourages deeper exploration and fosters independent learning.

    3. Using AI as a coach: Increasing Metacognition

    One role of a coach is to help students develop metacognitive skills. Metacognition involves reflecting on past experiences and effectively fostering behavioural changes in response. This report suggests that teachers often lack sufficient time to provide individualised coaching alongside their other teaching responsibilities – which, fortunately, AI can do a good job at.

    Metacognitive exercises facilitated by AI tutors can assist students in generalising their knowledge and deriving meaning from their experiences. By distilling meaning from these and considering alternative perspectives, students can develop a broader context for their learning.

    High-impact CPD made easy. Develop evidence-informed CPD at your school, using our exclusive online collection of courses and resources.

    4. Using AI as a teammate: Increasing collaborative intelligence

      Collaborative intelligence refers to the collective knowledge and skills of students working together to solve problems, complete tasks and achieve learning goals. Through collaborative intelligence, students are encouraged to share ideas, perspectives and resources creating a sense of teamwork within the classroom.

      This report suggests that embracing AI as a teammate can help aid students’ learning experience by fostering collaboration, encouraging them to engage in discussions, problem-solve and actively participate in work. Additionally, AI can act as a “devil’s advocate,” challenging teams to question assumptions and consider alternative viewpoints.

      5. Using AI as a student: The power of teaching others

      One of the most potent learning methods is to teach others; also known as the Protégé Effect. Explaining concepts to someone else can help students identify gaps in their knowledge, correct misconceptions, and better organise their knowledge.

      This report suggests that students can use AI as someone to teach to, by prompting it to explain a topic and then identify what it got wrong or missed. By explicitly naming what the AI gets wrong or right and teaching the concept to the AI, students can challenge their own understanding and question the depth of their knowledge.

      6. Using AI as a simulator: Creating opportunities for practice

      This report suggests that students use AI to practise the skills they have learnt, for example by asking it to build a role-playing scenario, prompting realistic ethical dilemmas or practice scientific experiments in a controlled virtual environment.

      These simulations bridge the gap between theoretical knowledge and practical application, really testing your students’ knowledge and honing their skills. Furthermore, AI simulators can help reduce cognitive load when learning – making it easier to learn and remember new things.

      7. Using AI as a tool: Checking for understanding

      In general, AI tools offer versatile applications, providing students with a safe and controlled space to practise and apply their knowledge. These innovative tools not only enhance the learning experience but also enable students to really grasp and explore complex concepts in many ways.

      One powerful way to do this is by students checking for their own understanding, making themselves less error-prone in their learning as a result. According to Rosenshine’s sixth Principle of Instruction, asking good questions is a great way to do so.

      This blog about the four question types to use to check knowledge and understanding can help you identify ways to best prompt an AI tool to assist with this task.

      Final thoughts

      The integration of AI in the classroom offers good potential opportunities for students. These seven approaches could support students’ academic success and learning. The key to it appears to be understanding what makes a good prompt – the better the prompt, the higher-quality the output. If students can master that, then hopefully AI can be a help, not a hindrance.


      About the editor

      Bradley Busch

      Bradley Busch

      Bradley Busch is a Chartered Psychologist and a leading expert on illuminating Cognitive Science research in education. As Director at InnerDrive, his work focuses on translating complex psychological research in a way that is accessible and helpful. He has delivered thousands of workshops for educators and students, helping improve how they think, learn and perform. Bradley is also a prolific writer: he co-authored four books including Teaching & Learning Illuminated and The Science of Learning, as well as regularly featuring in publications such as The Guardian and The Telegraph.

      Follow on XConnect on LinkedIn