The below prompt was used to generate high- and low-quality answers for a Year 9 Physics class learning about terminal velocity. This topic istypically academically challenging for Y9 pupils, as it requires a multi-stepexplanation as well as spatial and logical reasoning.
“You are an expert Physics teacher with an in-depth knowledge of pedagogicaltechniques and decades of experience in helping pupils learn. Your Y9 class arestudying Edexcel IGCSE Physics and have just finished learning about terminalvelocity and are now about to answer the following question: “Explain how askydiver reaches terminal velocity”. Write two answers to this question. Oneshould be an exemplar answer achieving full marks. The other should containseveral mistakes and misconceptions receiving very few marks. Limit each answerto 150 words. Explain why the great answer is great and why the bad answer iswrong. Ask me some clarification questions first and then produce the answers.”
The prompt was input into ChatGPT, whose outputs were then improved withfurther prompting (mostly to increase the length of the initial answers) andusing the teacher’s own subject and contextual knowledge of this topic in thescheme of work (see outputs below). The process was relatively quick (approx.20 minutes from start to finish).
Having first been taught the topic using more traditional methods, pupils werethen given a printed version of the high-quality answer which they evaluated ingroups of three. This promoted a useful discussion about logical structuring,naming the forces involved and the importance of giving their directions.
Pupils were then given the low-quality answer and, again in their groups, hadto discuss and find the common misconceptions. In this topic, where there arelots of common mistakes, this was an incredibly useful exercise in highlightingto pupils what sort of errors they might make and the importance of relevantdetail in their answers.
This task was then followed up with independently completed exam questions onthis topic to offer pupils further opportunities to deploy their understandingand embed this learning. The pupils scored well on a similair question in theirend of topic test.
The scenario in this case study is genuine and based upon real events and data, however its narration has been crafted by AI to uphold a standardised and clear format for readers.
Key Learning
This was a beneficial exercise that I feel improved thequality of my teaching and pupils’ understanding of this topic. Pupils writtenanswers following this task were notably well structured and avoided commonmisconceptions. In previous years, I would not have included a task like thisin my lessons. To write my own high- and low-quality answers would be overlytime consuming, as would collecting previous pupils’ work to be stored forfuture years.
Teacher input remains crucial so that the output from the AI can be adapted to retain its relevance to the exam board and educationalcontext of the class. I feel the outputs could be improved further by alsoinputting a mark scheme to the initial prompt, to give the LLM a clearercontext of what a model answer would include.
Pupils knowing the work was AI generated revealed a hiddenbenefit – they were far more willing to honestly critique and evaluate the workof AI than they would be a peer, leading to more open and frank reflection onthe answers during the discussion task. I will be continuing to use this promptto guide pupils through the writing of longer written questions.
Generic version of the prompt you can adapt: Youare an expert <subject> teacher with an in-depth knowledge of pedagogicaltechniques and decades of experience in helping pupils learn. Your Y<x>class has just finished learning about <topic> and are now about toanswer the following question: <>. Write two answers to this question.One should be an exemplar answer achieving full marks. The other should containseveral mistakes and misconceptions receiving very few marks. Limit each answerto <x> words. Explain why the great answer is great and why the poor answer is wrong. Ask me some clarification questions first and then produce theanswers.
Risks
The answers produced need to be thoroughly reviewed andadapted by the teacher to ensure they are in the desired style and are relevantto the class’s context.
Providing both the high- and low-quality answerssimultaneously can introduce a large cognitive load on pupils and risk themconflating the two.
By giving pupilsa high-quality answer ready to go, there is a risk that they will be less able to evaluate ideas and produce similaranswers independently in new scenarios.
