Skip to main content

Ways to use Chat GPT* for resource creation

 * and other generative AI tools such as DeepSeek, Gemini, Copilot and the rest.


I don't know about you, but I am finding generative AI a tremendously useful tool for creating lesson materials. The free version of Chat GPT is my go-to, though I have dabbled with DeepSeek which seems at least as good.

I posted on the GILT Facebook group recently about a few ways I have been using Chat GPT in recent months and asked group members what uses they had found for it. I am focusing here on written text uses rather than the more techie uses which I have not delved into so far.

So in this post I'll list some ways I have been using Chat GPT and will also mention the uses that teachers shared on FB. You may not have thought of all of these. 

Copying language from sentence builders (substitution tables) to create narrow listening and reading tasks. This makes sure that chunks are recycled in different ways. For anyone not sure what I mean by narrow reading/listening - this is where you produce, say, four short texts flooded with the same useful chunks so that students see or hear them multiple times. Hopefully, many of them stick. Alternatively, just ask Chat GPT to create four or more short texts from scratch. Remember that you can choose the difficulty level using the CEFR scale. For Y7-9 I would try A1. For GCSE, try A2.

Writing texts from scratch on specific topics. Recently, this has included a beginner text with a parallel translation called 'A day in the life of a cat'. Chat GPT created for me a list of true/false statements baed on the text, as well as the translation. At advanced level, Chat GPT created two versions of an invented fairy tale with 15 differences between the two texts. This created an information gap task. I also got Chat GPT to write me a text about islamophobia in France, along with comprehension questions and a 'Tick the correct statements' task.

Adapting and updating existing text resources. For example, I have been adding multi-choice questions and 'tick the correct sentences' to older resources. I have also used Chat GPT to updated facts and figures on informational texts, such as one on family life in France. I prompted the tool to check some existing figures from the INSEE site. 

Creating dialogues. For example, recently I had Chat GPT create a dialogue between two young French speakers about DEI programmes (Diversity, Equity and Inclusion). I like that it's possible to create a resource very quickly on topical issues. At novice level I created very basic dialogues to read aloud and adapt on the topics: me, where I live (house) and my town. For adult learners I produce a basic dialogue to read aloud and adapt about the town or city people live in. 

Creating 'knowledge portfolios'. Knowledge portfolios is the name I give to booklets of facts and figures about A-level sub-themes. These have been well-received in the past, but they were beginning to get out of date, so I got Chat GPT to produce newer information (up to 2024), together with sources.

Creating grammar drills. For example, an oral or written drill to translate and alter simple sentences in present and perfect tense. I recently created a matching task to practise question formation by prompting Chat GPT to give me 20 answers matched with 20 shuffled questions which would have produced them - an instant matching task. You can prompt Chat GPT to produce various drills based on a specific topic area, so that they are not quite so 'mechanical' and reinforce topics you are working on at them.

Spot the differences listening tasks. For intermediate/GCSE level Chat GPT created two easy listening texts with 10 differences. Students would have to listen to the teacher reading them aloud and note where there are differences.

Creating vocab matching tasks. For example, I used this prompt: "Give me a list of 10 sports in French, with a definition in French for each sport. The actual name of the sport must not be mentioned in the definition." The resulting definitions can be used as a reading or listening matching task. For instance, the teacher reads a definition and students must identify the sport, with or without reference to a list of sports.

Creating gap-fill tasks. An obvious one maybe, but you can vary the prompts to include, for example, short chunks rather than isolated words. or you can prompt Chat GPT to produce a short text on an easy topic you have been working on, but with the vowels missing. This is yet another example of a task you might have designed yourself, but which would have taken much longer.

'Disappearing text.' This is a gap-fill variation which you may know of already. Here is a prompt I used: "Now take the family text you wrote and produce three more versions of the text, each one with progressively more gaps to fill. Each gap must begin with the first letter of the missing word." Chat GPT did this perfectly. You could copy in the gapped texts into PowerPoint slides or a Word document for display to make it a teacher-led activity.

Multiple choice. These are very time consuming to produce, but AI does them almost instantly. Specify the type of prompt (question or sentence completion) and the number of response options. Results are not always subtle, but you can always edit to some extent. I’ve noticed that when three options are specified, Chat GPT has a bias towards option B. You can ask it to avoid this.

Creating full lesson plans. For example, I prompted Chat GPT to create a lesson plan on the climate crisis,including a 150 word text, true/false, multi-choice, comprehension questions in English and French. I added my own instructions for the teacher, along with a couple of extra elements and options.

Here are other uses that the GILT Facebook teachers shared:

  • I was taking a grade class on Italian geography and had to come up with 2 lesson plans a week. Some of the topics were a bit dry and not completely relatable for middle school. So I had Chat GPT create simple stories centered around a teenager using the topics and created activities to go with those texts.
  • I use it when I'm teaching the films at A level, I write my little text on the point we're studying, then I copy and paste with the question "have I missed anything?" It puts it into a nicer flowing text. I also use it to write sample essays.
  • For GCSE, I ask it to create translation exercises with particular points of grammar that my students are finding tricky in the translation tasks
  • Get my chunks or sentences from sentencebuilders.com and get GPT to turn them into sentence puzzles, gapfill, anagrams, tangled translations etc. 
  • To replicate a given sentence structure using a single key difference. 
  • To create short texts I then put into Narakeet for listening/aural and save my own voice. 
  • Upload a picture and write a sample description based on given vocab.
  •  One of the things I like to do is give it a list of say 10-12 new lexical items and ask it to give me 3 short sentences per item targeted at learners, with English translations. Then I’ll paste them into your multiple choice quiz of choice so that students can preview new vocabulary in a fun way before we get stuck into a series of comprehension and structured production tasks.
  • I've used it recently for GCSE revision to pull out role play question examples from previous papers etc which I've then used in revision activities.
  • I upload the vocab list from Foundation and Higher Tier lists at GCSE and have it write two texts - one for each level - and ask to do gap fill questions and multiple choice questions in the Edexcel exam style

Comments

Popular posts from this blog

What is skill acquisition theory?

For this post, I am drawing on a section from the excellent book by Rod Ellis and Natsuko Shintani called Exploring Language Pedagogy through Second Language Acquisition Research (Routledge, 2014). Skill acquisition is one of several competing theories of how we learn new languages. It’s a theory based on the idea that skilled behaviour in any area can become routinised and even automatic under certain conditions through repeated pairing of stimuli and responses. When put like that, it looks a bit like the behaviourist view of stimulus-response learning which went out of fashion from the late 1950s. Skill acquisition draws on John Anderson’s ACT theory, which he called a cognitivist stimulus-response theory. ACT stands for Adaptive Control of Thought.  ACT theory distinguishes declarative knowledge (knowledge of facts and concepts, such as the fact that adjectives agree) from procedural knowledge (knowing how to do things in certain situations, such as understand and speak a langua...

The 2026 GCSE subject content is published!

Two DfE documents were published today. The first was the response to the consultation about the proposed new GCSE (originally due in October 2021) and the second is the subject content document which, ultimately, is of most interest to MFL teachers in England. Here is the link  to the document.  We are talking about an exam to be done from 2026 (current Y7s). There is always a tendency for sceptical teachers to think that consultations are a bit of a sham and that the DfE will just go ahead and do what they want when it comes to exam reform. In this case, the responses to the original proposals were mixed, and most certainly hostile as far as exam boards and professional associations representing the MFL community, universities, head teachers and awarding bodies are concerned. What has emerged does reveal some significant changes which take account of a number of criticisms levelled at the proposals. As I read it, the most important changes relate to vocabulary and the issue ...

La retraite à 60 ans

Suite à mon post récent sur les acquis sociaux..... L'âge légal de la retraite est une chose. Je voudrais bien savoir à quel âge les gens prennent leur retraite en pratique - l'âge réel de la retraite, si vous voulez. J'ai entendu prétendre qu'il y a peu de différence à cet égard entre la France et le Royaume-Uni. Manifestation à Marseille en 2008 pour le maintien de la retraite à 60 ans © AFP/Michel Gangne Six Français sur dix sont d’accord avec le PS qui défend la retraite à 60 ans (BVA) Cécile Quéguiner Plus de la moitié des Français jugent que le gouvernement a " tort de vouloir aller vite dans la réforme " et estiment que le PS a " raison de défendre l’âge légal de départ en retraite à 60 ans ". Résultat d’un sondage BVA/Absoluce pour Les Échos et France Info , paru ce matin. Une majorité de Français (58%) estiment que la position du Parti socialiste , qui défend le maintien de l’âge légal de départ à la retraite à 60 ans, ...