2.X. Cross-Curricular: AI-Assisted Lesson Design

From AI-Generated ConversationsPrompt to NaturalClassroom-Ready EnglishLearning Activity

Subject: EnglishCross-curricular as/ aTeacher ForeignProfessional LanguageDevelopment  ·  Grade:Target Group: 9Teachers (ageand 14–15)educators  ·  Duration: 1 double lessonworkshop (90 min) ·  AI: LearningTeaching WITH AI 

AI-related competencies (DUAL.AI.TEACHer Framework) – teacher level

Subject-specific learning objectives – student/learner level

AF-DR-2b (AI Foundations and Applications × Digital Resources, Level 2 – Reflective Implementation):   “Teachers can implement prompting, iteration, and refinement strategies to obtain usable AI-generated resources.”   AF-TL-2b (AI foundationsFoundations and applicationsApplications × Teaching & Learning, Level 2 – Reflective Implementation):   “Teachers can organise lesson elements that embed AI use with clear pedagogical roles and strategies to verify the output elements.”   AF-FC-2b (AI foundations and applications × Facilitating Learners’ (AI) Digital Competence, Level 2 – Reflective Implementation):   “Teachers can implement guidance that helps learners develop practical AI skills, adapting the tasks to learners’ prior knowledge and the AI tools available.”

By the end of the lesson, studentsparticipants can: distinguishformulate between grammatically correct and contextually appropriate English; identify differences in vocabulary, tone and register across communicative situations; formulatea structured promptsprompt thatfor specifycreating audience,a purpose,learning context,activity language level and tone; compare AI-generated language and identify inappropriate or unnatural formulations; revise AI-generated language usingin their own linguisticsubject judgement;area; check whetherevaluate an AI-generated responseactivity followsfor pedagogical relevance, accuracy and suitability for the requirementstarget givengroup; inidentify elements of AI-generated material that require human verification or adaptation; improve an initial AI output through prompting, iteration and manual revision; integrate AI into a prompt.lesson while maintaining a clear pedagogical role for the teacher and learner.

Take-home message: Generative AI can generateaccelerate fluentlesson and grammatically correct English,preparation, but thisa doesusable notlearning automaticallyactivity makerarely comes from a single prompt. Effective AI-supported lesson design is an iterative process in which teachers define the languagepedagogical naturalgoal, orgenerate appropriateideas, for a particular situation. By changingevaluate the audience,output, purposerefine it and context of an AI-generated conversation, students learn to evaluate AI suggestions and use their own language knowledge to make the final instructional decisions.

Fig 1. Image generated with ChatGPT (GPT Image 2), September 1, 2026.

Content

Communicating successfully in a foreign language requires more than producing grammatically correct sentences. Speakers constantly adapt their vocabulary, sentence structure, politeness and tone according to the audience, purpose and context of communication. The same intention can therefore be expressed in very different ways depending on who is speaking to whom. A request made to a close friend may be short and informal, while the same request addressed to a teacher, employer or unfamiliar person usually requires different vocabulary, more polite structures and a different degree of formality. These differences are part of register, which describes how language changes according to the social and communicative situation.

For language learners, register can be difficult to recognise because a sentence may be grammatically correct while still sounding unnatural or inappropriate in a particular context. Textbook examples often provide clear distinctions between formal and informal language, while real communication is much more flexible. Age, relationship between speakers, cultural expectations, medium of communication and communicative purpose can all influence the language that is used. A message that sounds natural in a conversation between teenagers, for example, may sound too informal in an email to a teacher, while an expression that is suitable for a formal letter may sound unnecessarily distant in everyday conversation.

Generative AI can producesupport teachers with many tasks involved in lesson preparation, including generating activity ideas, adapting materials to different learner groups, producing examples and adaptquestions, dialoguesor verysuggesting quickly,alternative whichways makesof itexplaining usefula topic. The Latvian Datorium case study demonstrates this practical approach to teacher AI competence development: teachers first become familiar with AI and its educational applications and then move towards practical experimentation, lesson planning, assessment and differentiated material development. Classroom application is followed by reflection and feedback, making AI use part of an iterative professional learning process rather than a one-time technical exercise.

The usefulness of generative AI for exploringlesson thesedesign differences.depends Byheavily changingon individualthe elementsinformation ofand aconstraints prompt,provided by the teacher. A request such as “Create a lesson about climate change” leaves most pedagogical decisions to the relationshipAI betweensystem. speakers,A languagemore level,structured purpose or degree of formality, learnersprompt can generate several versions ofspecify the samesubject, communicativelearner situationage, existing knowledge, learning objective, duration, teaching method, available resources and compareexpected howlearner output. Adding these elements does not guarantee a good lesson, but it gives the languageteacher changes.greater Atcontrol over what the sameAI time,produces AI-generatedand languagemakes isthe notresulting automaticallymaterial reliableeasier simplyto becauseevaluate itagainst soundsthe fluent.intended Alearning modelgoal.

may

Even a detailed prompt can produce languagematerial that is toofactually formal,inaccurate, repetitive,pedagogically culturallyweak, awkward,unrealistic inconsistentfor the available lesson time or unsuitable for a particular group of learners. AI may suggest activities without considering classroom dynamics, assume resources that are unavailable, generate tasks that do not actually measure the stated learning objective, or provide content that appears convincing but requires factual verification. For this reason, AI-generated educational material should be treated as a draft rather than a finished teaching resource.

The central learning process in this activity is therefore not simply learning how to write a “good prompt”. Teachers work through a repeated cycle of define → prompt → evaluate → refine → verify. They begin with a real learning objective from their own teaching context, use AI to propose an activity, evaluate the result against pedagogical criteria, refine the prompt where necessary and finally make their own modifications before the activity is considered classroom-ready. This reflects the Datorium case study's emphasis on practical experimentation, co-creation, classroom application and reflection, while keeping pedagogical responsibility and validation with the requested level or not fully aligned with the instructions given in the prompt. Generative AI also works probabilistically, which means that similar prompts can produce different formulations.

This limitation is central to the activity rather than something to hide from learners. AI becomes most useful when students treat its output as language material to analyse rather than an answer to accept. In this lesson, students first examine how register changes across communication contexts and then use an LLM to modify one communicative variable at a time. They compare the resulting dialogues, identify which linguistic choices work and which do not, and revise parts of the output themselves. In this way, students practise both communicative competence in English and practical AI literacy: giving clear instructions, checking whether those instructions were followed and using their own linguistic judgement to decide whether the final result is appropriate.teacher.

Lesson plan

Phase	Time	Activity
Introduction	10 min	TheParticipants teacheridentify showsone twolesson-preparation short messages communicating the same request,task for examplewhich oneAI addressedcould topotentially abe frienduseful. andThe anotherfacilitator tointroduces aAI teacher.as Studentsan identifyassistant/co-creator differencesrather inthan vocabulary,an politenessautonomous andlesson tone and suggest who might have written each message.designer.
Input	1015 min	TheParticipants teachercompare introducesa simple prompt with a structured educational prompt and examine how additional context changes the conceptsgenerated oflearning audience, purpose, context and register. Together, students identify features of formal and informal English and discuss why grammatically correct language is not necessarily appropriate language.activity.
Exploration	15 min	InEach pairs,participant studentsselects examinea real learning objective from their subject and asks an LLM to generate a short AI-generatedclassroom dialogueactivity foraddressing an everyday situation. They identify useful expressions and highlight anything that sounds unnatural, too formal, too informal or unsuitable for their English level.it.
Adaptation	35 min	StudentsParticipants work through 2–3two or three rounds of predict → prompt → compareevaluate → diagnose.refine In→ eachverify, round,progressively theyadding changepedagogical oneconstraints aspectand ofchecking the communicationresulting context and ask the AI to adapt the dialogue.activity.
Reflection	2025 min	StudentsParticipants compare their versionsoriginal AI output with the final classroom-ready version and discussidentify which changesimprovements affectedcame thefrom language most. They identify where AI followed the instructions well, where it did not,prompting and which expressionsrequired theytheir wouldown changeprofessional themselves.judgement.

Guiding questions: layeringfrom complexityAI output to classroom-ready activity

Pairs work through as many of the following rounds as time allows during the 35-minute adaptation phase. Most pairs should complete two rounds, while the third can be used as an extension:

1. Round 1 — ChangeDefine the relationshippedagogical betweenpurpose:
   speakers:

   Before prompting the AI, define:

   • Predict:Who Imagine thatare the samelearners?
   request
2. What should they know or be able to do?

What prior knowledge do they have? How much time is madeavailable? toWhat ashould closelearners friendactually do during the activity?

Generate an initial activity and tocompare ait teacher. What do you expect to change? Think about vocabulary, greetings, sentence structure and politeness.

Prompt: Askwith the AIintended tolearning rewrite the dialogue for a different relationship between the speakers.

For example:objective.

Rewrite this conversation between two friends as a conversation between a student and a teacher. Keep the meaning the same, but use polite, natural English suitable for a B1 learner.

Compare: Compare the original and new dialogues. Identify at least three linguistic changes.

• Diagnose: DidDoes the AIactivity changeactually onlyhelp individuallearners words,achieve the objective, or diddoes it alsomerely changerelate sentenceto structure,the greetings,same requests and closing expressions? Which changes are appropriate? Is there anything you would change yourself?topic?

Round 2 — ChangeAdd classroom constraints:

Refine the communicativeprompt purpose:
by

Studentsadding nowrealistic changeconditions whatsuch oneas speakerclass wantssize, toavailable achieve.materials, Forlesson example:duration, learner level, teaching method or accessibility requirements.

asking for information → making a complaint

accepting an invitation → declining politely

asking for help → requesting permission

informal conversation → formal request

Predict: What language do you expect to change whenGenerate the purposerevised ofactivity and compare it with the conversationfirst changes? Prompt: Create a more detailed prompt that includes: speaker + situation + purpose + language level + tone

For example:version.

Create a short B1-level dialogue between a customer and a café employee. The customer received the wrong order and wants to solve the problem politely. Use natural everyday English and keep the dialogue to eight lines.

Compare: Check whether the generated dialogue follows each part of the instruction.

• Diagnose: SelectWhich onechanges expressionimproved thatthe worksactivity? wellWhat andclassroom oneconditions thathas youthe wouldAI rewrite.still Explainfailed why.to consider?

Optional round 3 — Add constraintsVerify and challengetake back control:

Evaluate the AI:final

StudentsAI-generated makeactivity their instructions more specific.for:

For example:

Rewrite the conversation for two 15-year-olds. Keep the English at B1 level. Make it friendly and natural, but avoid slang. Keep the same communicative purpose.

• Predict:factual Whichaccuracy;

partsalignment with the learning objective; suitability for the learner group; realistic timing; clarity of the previous dialogue do you expect to change?instructions; Prompt:accessibility Askand theinclusion; teacher and learner roles.

Participants then make at least one manual change without asking AI to producerevise it.

The final comparison is therefore not “Which prompt produced the revisedbest version.AI Compare:answer?” Checkbut therather response against every requirement in the prompt. “Diagnose: Which instructionsWhat did the AIteacher followhave successfully?to Whichcontribute didto itturn ignorean orAI-generated interpretidea differently?into a usable learning activity?”

Closing question (for the Reflect phase): At which point did changing the communicationAI-generated situationactivity require more than simply replacingimproving athe few words,prompt, and what does this tell you about communicatingthe effectivelyteacher’s role in anotherAI-supported language?lesson design?

Follow with: If an AI-generated dialoguelearning isactivity grammaticallyappears correct,complete and well structured, how can you decide whether it is actually pedagogically appropriate and naturalready forto thisuse particularwith situation?learners?

Materials

• One laptop or tablet per student pair,participant, with a browser
• Access to an approved LLM chat interface via the internet,interface, or a locally installed model if internet access is restricted at school
• One shortreal starterlearning dialogueobjective ator approximatelylesson B1topic levelfrom each participant's teaching context

A structured educational prompting template A short prompting / worksheet template for the adaptation rounds (predictdefine → prompt → compareevaluate → diagnose)refine → verify cycle AAn language-evaluation checklist covering meaning,pedagogical grammar,relevance, vocabulary,accuracy, register,learner naturalnesssuitability, feasibility and fulfilmentalignment with learning objectives Example of instructionsa Teacher-preparedsimple examples of formalprompt and informala communicationmore Astructured shorteducational AI-use guideline reminding students not to enter personal information and to treat AI-generated language as material to analyse and improve, not as an answer keyprompt