Your Partner For Ideas: A Framework

AI as a Partner for Ideas: A Journey to Transformative Education

Imagine finding a solution to a persistent challenge in minutes—a challenge that has been a roadblock for weeks in your teaching, curriculum design, or school improvement plan. Generative AI offers this potential, yet its true value is often misunderstood in education. This isn’t about using AI to automate attendance records or streamline email communications. It’s about transforming leadership, subject planning, finding creative outlets where existing ideas have dried up and collaborative thinking in schools. AI isn’t here to replace the expertise of educators; it’s here to amplify it. The question is: Are we ready to guide AI, or are we letting it guide us? Because, upon reading this from the Harvard Business Review and applying it to my recent presentations both here and at my school.

Presentation (Silent): The recent AI presentation I ran at my school, click to play

Moving Beyond Routine Uses and Amplify Your Ideas

For many educators, the default use of AI is transactional—marking quizzes, drafting newsletters, or producing quick lesson ideas. While helpful, these uses only skim the surface. AI’s transformative potential begins when educators ask a deeper question: How can AI help me do this?

Reframing AI as a collaborative assistant rather than a simple INPUT/OUTPUT tool reveals its full value. Teachers, department heads, and school leaders remain the visionaries, setting goals and defining challenges. AI supports them by synthesising vast amounts of data, stress-testing curriculum ideas, or suggesting creative solutions to enhance student learning outcomes. For example, AI can help analyse assessment results across year groups, propose differentiated learning strategies, or suggest innovative ways to implement an inquiry-based curriculum.

But this dynamic only works if educators remain firmly in control. Without clarity of purpose and leadership, AI risks becoming a gimmick—efficient, yes, but directionless. The shift, therefore, is not simply about using AI better; it’s about reimagining how educators and leaders partner with technology to create meaningful innovation in schools that can cover all aspects of the community.

A Basic Framework for Transformative AI Use in Education

As I’ve been running sessions on how to apply a Design Thinking process to working with an LLM there are some finer aspects that need to run in parallel to gain control, lead the AI and to allow the AI to guide one’s focus. To use AI as a genuine partner for your ideas in education, a structured framework is essential. This framework is built on four critical components:

1. Context: Clearly define the problem or goal. Whether it’s improving student engagement, planning cross-curricular projects, or streamlining administrative tasks, AI thrives on detailed input so give it as much input on what the idea, problem or goal is.

2. Role Assignment: Treat AI as an expert collaborator—a curriculum advisor, a data analyst, or a creative project planner. Assigning a specific role helps focus its output. Say “You are a dedicated author and global leader in primary/ secondary/ tertiary education…” or “ Your role in helping to solve this problem is as a school leader of a large, prestigious and highly recognised school or X, where Y is the sticking point…”,

3. Interviewing: Engage AI interactively. Ask it to pose clarifying questions about your context, whether it’s a departmental goal or a challenge in school leadership. This dialogue sharpens your input and improves results. In thsi case, task the AI with asking pertinent questions one at a time for the AI to collate a picture of the people, the scenario and challenge at play. This way, the task becomes easy to clarify.

4. Task Definition: Clearly outline what you want from AI—whether that’s lesson scaffolding, an improvement plan for literacy, or insights into staff wellbeing surveys.

Imagine a subject leader tasked with introducing a new inquiry-led science programme. By assigning AI the role of curriculum advisor, they could brainstorm lesson structures, explore links to real-world applications, and develop strategies for assessing inquiry skills. This isn’t about handing over control; it’s about amplifying expertise through thoughtful collaboration.

The 20% That Drives 80% in Schools

The greatest value of AI lies in addressing high-stakes, strategic challenges—the “20% activities” that drive 80% of impact in education. These are the big challenges: improving outcomes in literacy or numeracy, creating a school-wide programme to boost critical thinking our outcomes, or fostering equity for EAL or high achievers in classroom practices.

Too often, AI is used for mundane, low-impact tasks like compiling attendance data or generating generic worksheets. While useful, these applications don’t tap into its transformative potential. Instead, imagine applying AI to redesign curriculum planning across year groups or create a school-wide strategy for integrating project-based learning. AI could propose interdisciplinary connections, identify gaps in curriculum coverage, or generate practical approaches for differentiated instruction.

These are not surface-level fixes but deep insights that challenge assumptions and inspire action. When school leaders and educators frame AI inquiries thoughtfully and stay engaged with the process, they open doors to strategies and possibilities that would otherwise go unexplored. Which, when we’re at this stage, why not ask “From this scenario, what unexpected pitfalls might I face with this group, this person, this subject planning if X is there or given this goal’s aim and cost who’s likely to object to…?”

Embedding AI Into Educational Routines

For AI to become a natural part of educational leadership and planning, it must be woven into daily and weekly routines. Establishing a habit of interacting with AI ensures it becomes a consistent partner, not just a sporadic tool.

One approach is to dedicate time during staff meetings or departmental planning to engage with AI. For instance, teachers might use it to brainstorm differentiation strategies for upcoming topics or develop creative formative assessment methods. Another method is reflective journaling with AI. School leaders could begin each week by outlining their key goals—such as improving staff retention or analysing attainment data—then use AI to generate actionable insights.

These practices create a rhythm of collaboration between educators and technology, fostering reflective thinking and strategic focus. Over time, the habit of working with AI strengthens both individual practice and collective planning across teams, leading to better outcomes for students.

The Teacher and Leader’s Role

At the core of AI integration in education is a critical truth: teachers and school leaders must lead. AI excels at processing data, identifying patterns, and suggesting ideas, but it cannot replicate the intuition, empathy, and values that drive education. These uniquely human traits are what make schools effective and inspiring.

Leaders must define the purpose, guide the process, and critically evaluate AI’s outputs. Consider a headteacher drafting a strategic improvement plan for the school. AI might suggest useful frameworks or identify trends from school-wide data, but the leader decides how these align with the school’s vision and community needs. Teachers can use AI to co-develop project plans or assess curriculum gaps, but it’s their professional judgment that determines the path forward.

This balance—where human expertise guides technology’s capabilities—is the key to meaningful educational progress. AI enhances creativity, supports decision-making, and expands possibilities, but it must always serve the goals set by educators and leaders.

A New Era for Education

The integration of AI as a creative assistant represents a profound shift in how schools innovate and improve. It challenges the traditional view of technology as a passive tool, instead reframing it as a collaborative force for tackling complex educational challenges. This is not about replacing human expertise but amplifying it—enabling educators and leaders to plan more creatively, think more strategically, and act with greater impact.

It all begins with a question: How can AI help me achieve this? Asking this regularly transforms AI from a convenience into a partner, unlocking a powerful harmony between educational vision and technological capability. This partnership has the potential to reshape curricula, foster better collaboration, and create far more creative learning experiences.

The question is not whether AI can contribute to schools—it is whether educators are ready to lead it with clarity and purpose. Those who embrace this challenge will find themselves at the forefront of a new era, where technology and education work together to create extraordinary outcomes. What could you or your school achieve if AI became your creative assistant today?

AI as Your Learned Partner in Contemporary Education

As educators, we’ve weathered waves of technological innovation, each heralded as the end of traditional teaching as we know it. Calculators were supposed to render the instruction of maths obsolete, and interactive whiteboards were going to revolutionise the classroom. Yet here we stand, still led by the dedicated teachers who form the heart of education.

Presenting at AI For Education, Verso School, Bangkok.

At the recent AI in Education Conference, hosted by Verso International School and 21st Century Learning, this narrative took centre stage. Far from declaring that artificial intelligence will replace teachers, the conference emphasised a more balanced perspective: AI is a tool to enhance teaching, not a replacement for human educators.

This distinction is critical. AI can generate endless practice problems, analyse patterns in student performance, and provide instant feedback. These capabilities free educators to focus on what truly matters—fostering curiosity, encouraging critical thinking, and supporting students’ emotional and creative growth. Imagine a teacher using AI to generate personalised learning pathways for every student, allowing them to spend more time coaching, inspiring, and connecting.

Dr. John Nash Presenting his Keynote at the conference.

Yet, as the discussions at Verso made clear, AI is no silver bullet [echoing Ethan Mollick more than once]. It cannot replicate the nuanced, lived-in expertise of a teacher. Only a teacher can observe a student's anxiety, adapt lessons to the energy in the room, or offer the empathy that transforms a struggling learner into a confident one. These human qualities remain irreplaceable, underscoring the importance of augmenting the practice of human educators with artificial intelligence.

The question isn’t whether AI will take over teaching. It’s how educators and schools can use it creatively, responsibly, and effectively to enhance their work. As participants explored at the conference, the integration of AI must be guided by clear goals, ethical considerations, and an unwavering commitment to the human element of education. Just yesterday, Apple and Dr. Sabba Quidwai were expressing the same sentiments.

The Ethical Imperative: Frameworks for AI in Education

The rapid adoption of AI in schools requires robust ethical frameworks to guide its integration which was a recurring theme at the conference. The discussions emphasised that technology, for all its potential, is only as good as the values behind its use.

A powerful example discussed was stakeholder mapping—a process of identifying the roles, concerns, and responsibilities of everyone impacted by AI in education:

• Teachers need to maintain authentic human connections while ensuring that AI supports their expertise.

• Parents want transparency about data usage and assurances that AI won’t undermine teacher-led learning.

• Students require clear guidance on AI use, with safeguards to prevent over-reliance on its capabilities.

By addressing these concerns collaboratively, schools can build trust and ensure that AI aligns with their core values. Consider data privacy (The EU’s Right to be Forgotten Laws)—a cornerstone of ethical AI use. Schools must adopt transparent policies and communicate openly about how student data is handled.

The conference also stressed the importance of keeping humans in the loop. Teachers and administrators must actively evaluate AI outputs for biases, inaccuracies, and ethical red flags. Without this active oversight, there’s a risk of ceding too much control to systems that lack judgment and accountability.

Ethical frameworks are about more than compliance; they’re about building a culture of trust, equity, and collaboration. The goal is clear: to ensure that AI serves to empower educators and students, not control them.

Practical Tools for AI Integration: Empowering Educators with Structure and Simplicity

Among the many insights shared at the conference, one of the most practical takeaways was the 6-Point Framework for AI Tool Evaluation. This framework provides educators with a systematic way to assess AI tools, focusing on:

1. Data Privacy: Is student data handled securely and ethically?

2. Educational Value: Does the tool align with and enhance learning goals?

3. Technical Reliability: Is the tool consistent and easy to troubleshoot?

4. Ease of Implementation: How much training and support is needed for teachers to adopt it?

5. Resource Requirements: Does the tool justify its time and financial costs?

6. Ethical Alignment: Does the tool reflect the school’s values?

The Hattiebot for visible learning via Claude/ ChatGPT

These criteria move the conversation from “Is this tool impressive?” to “Does this tool serve our purpose?” For example, a tool like Hattiebot —demonstrated at the conference—helps teachers design lessons using evidence-based strategies from John Hattie’s principles of visible learning. It simplifies planning, offering step-by-step guidance on defining learning intentions, setting success criteria, and incorporating high-impact teaching methods.

Tools like Hattiebot show how AI can streamline workflows, freeing teachers to focus on their students. The key takeaway: AI tools must enhance, not complicate, the teaching process.

Professional Development: Meeting Teachers Where They Are

For AI to be effective, professional development (PD) must address the diverse needs of teachers. The conference identified three key educator profiles, each requiring a tailored approach:

• Early Adopters: Confident and curious, these teachers need advanced training to use AI in more complex ways and can mentor others.

• Cautiously Interested Teachers: Curious but unsure, these teachers benefit from simple, low-risk AI tools that clearly show value without disrupting routines.

• Resistant Teachers: Sceptical teachers need to see how AI saves time and supports, rather than replaces, their teaching.

Effective PD emphasises hands-on examples and ethical considerations. For instance, a teacher hesitant about AI might try using Hattiebot to simplify lesson planning, experiencing its benefits firsthand. By addressing fears and building confidence through real-world applications, PD bridges the gap between scepticism and adoption.

Responsible AI: Ethical Considerations and Student-Centered Design

AI’s transformative potential in education comes with urgent ethical responsibilities. The conference repeatedly emphasised that data privacy, equity, and autonomy are not just technical details but foundational to how schools adopt AI.

For example, AI tools that generate personalised learning exercises or grade assignments must align with clear policies:

• Acceptable Uses: AI can support tasks like grammar checks, but should not complete work meant to reflect a student’s understanding.

• Prohibited Practices: Clear boundaries prevent misuse, such as AI-generated assignments that undermine academic integrity.

• Assessment Design: Define when AI can assist and when human judgment is essential, particularly for subjective tasks like essays or creative work.

Crucially, AI must enhance equity, ensuring that students from diverse backgrounds can access its benefits without creating new divides. Transparent communication with students and parents builds trust, ensuring that AI supports—not diminishes—the values of originality, creativity, and fairness.

At its core, the conference posed a powerful question: How can AI help us uphold what we value most in education? The answer lies in thoughtful integration, ethical practices, and a commitment to amplifying—not replacing—the human touch in learning.

Charting the Future of AI in Education

The message from the conference was clear: AI isn’t here to replace educators; it’s here to empower them. By embracing ethical frameworks, leveraging practical tools, and tailoring professional development, schools can ensure that AI serves their students, teachers, and communities effectively.

This is the future of education: where human expertise and artificial intelligence work hand in hand to inspire future learning.

21CL BKK: AI is Not Taking Our Jobs, Quite the Opposite: Midjourney Generative Art

This is a third part to creating generative resources in the classroom with the use of artificial intelligence. In this post, we are looking at what Midjourney via Discord can do for us.

Within this post, there will be an expectation to look into signing up to platforms, using apps, perhaps paying for apps or services such as Midjourney pro or, finding free/freemium/ open source alternatives to work alongside the process here.

Ai is not taking our Jobs, quite the opposite by Glenn Malcolm

Some prerequisites:

1. Discord. Free to use and sign up via app or web.

2. Midjourney Discord server. Free to view and use for 25 (x 4 - each image is a panel of 4 images, 100 inn total). Option to pay $10 per month.

3. Photoshop or similar. Photopea is a good web alternative.

4. Canva: an option to 3 for editing in a basic way - cutting, cropping etc. + below

5. Your Operating system’s image editor.

6. Optional: Comic book app or creator. Perhaps Canva has non-premium content. Adobe Express has many.

7. Optional: Storyboard templates.

8. Topic or theme you are working on with children for setting and character design.

9. Optional movie editing software such as iMovie, CN Movie Editor, Capcut or your choice.

At my school I run several ECAs. Part of these are animation ECAs that allow the children to get away from the humdrum curriculum constraints and let the children go to far reaches of their mined for wild ideas, stories and characters.

One day we are in the ECA and there was a brouhaha from the other side of the room where some children we getting more and more frustrated with the results a search was throwing up for them. I mean, all they wanted was ‘Lionel Messi slide tackling Buddha in the penalty area’ ‘Simba as a cub falling to his doom from a cliff in the African savannahs’ and ‘Alex from Minecraft riding an actual roller coaster’.

I dawned on me that the way children want to search coupled with the way they think search should behave is exactly the way Midjourney behaves. If you don’t know what Midjourney is then it’s like this search above and it kind of generates a version of this mental imagery as a selection of four options for you to either remix and get variations or ‘upscale’ the one you like. Much like the one below. This is part of 1940s comic book theme in the style of Al Williamson. The prompt here is: Al Williamson, comic book character, 1940s, film noir, rookie cop alone, no background, black and white, --ar 1:1

You’ll note that this is different to the children’s ideas and for good reason. In our 21CL BKK workshop we will be aiming for a type of consistent theme, character, setting object or product that we can use in our classes.

You may also note that there are some numbers at the end, a ‘style’ and specific instruction for the character I want. There are panels I want in my comic, so I ask for this too. This is only so I can get a flavour of what I might want to produce later on. A bit of inspiration or a type of mood board from the prompts.

Al Williamson,, comic book set in the 1940s, black and white, detective, film noir, action shot, 9 panels, color only yellow

Discord

To do this, we need to sign up to Discord. Create an account.

Then check out some AI servers.

Midjourney

Then find Midjourney here. Click and join. You can use the App, on your device or on the web.

Once you’re in Midjourney you have 20 general chats on the side. Choose one and look around. Scroll up and down to see that people are making. Look at the prompts. Some are long, very long or filled with added extras such —seed 1233040302 or —AR 16:9 or the like.

Explore

Either way see if you can work out what they do.

Here we can see the prompt. Simple and strange at the same time.

Let’s see what you get when you try the same prompt. As a rule, when you sign up, you are only give 25 free images in batches of four. You may want try this, or look at the showcase here to get a style you like.

Then we will get some ideas for a writing project, a creative arts project, animation, computer game deign idea or story prompts for your classes.

Might be good to write some prompts of your own in your phone, text or pen and paper. Then, drop them into a prompt creator like AI PRM if you would like to get some wild ideas and use ChatGPT to help out.

See the video below and the link here for the Chrome extension.

AI PRM - Prompt Creator in Chrome for ChatGPT

Create a Character

One of the first ideas you may have is character choice. For this example I am going to set up a series of four characters and use one as a main thread here. The reason for this is that we can end up creating comics as a series of characters, poses and settings. You can skip down to see the characters in the story I’ve made up.

The hard part, as you will discover, is getting consistent characters. But we can practice on this. If you are already a user of Midjourney, then you may want to gather some characters and download the images you want. Then, collect the links to them. If you want a video - go to the bottom of this post.

In the meantime, if you are a new user then please create an idea for a character in a story.

Younger Children’s Use of AI

As you may be thinking, how can I use this with younger children, it’s hard to without an adult or older students beyond 13 years old. If you would like to use this process with younger children in class, then perhaps Craiyon.com might help you.

From this prompt in Craiyon.com: al williamson style, black and white, 1940s, film noir, comic book character, rookie cop alone, full figure, standing facing front, no background, white paper, we get this result. Not quite the same but usable all the same as a storyboard or a starter character at least!

Making a Character

Let’s move on…

Things you need now are these:

1. character idea: man, woman, beast etc.

2. style: painting, comic book,

3. Artist style: Dali, Yayoi Kusama, Roy Lichtenstein, Bauhaus, 17th century Flemish, 21st century realism etc.

4. Colour choices.

5. Expressions.

6. Clothing: hat, cloak, chaps…

7. Character description: stopped, fat, thin, laughing, jolly, morose etc.

8. Background style: (below I have made a white backdrop as it’s a character sheet). Plain, busy, patterned, Fleur De Lys, Jungles, Desert, Frosty Tundra. Experiment, but for this exercise I am showing character only until later.

For this character introduction, we will only use a character sheet. The reason why is that we can download the one we want trim it in an editor and re-use it. The other reason here, is that we are training the generative part of the AI to understand what we want. This will allow us to keep this as consistent as possible and this is key if we are to make a series of character poses.

Once you have your idea, go to Midjounrney and in the sidebar, where it has #general-20 (any one is fine), and type: /imagine + your choices.

I typed this: /imagine woman comic book dali style red dress bouncing curly hair happy and jolly walking white background character sheet

Of course, you can bow out now and play with these selections if you are new to this. For those who have used this, then please carry on reading as I am going to explain the options we have and why we need to keep track of this as it develops.

Going Further

Above, we can see the part finished image with about 20% finished. You can see though that the character is clearly coming through with the clothing and shape on the white background.

The video below, you can see that I am using the MidJounrney app on Mac, I’ve chosen the #general-3 channel. In here you can see my prompt: /imagine woman comic book dali style red dress bouncing curly hair happy and jolly walking white background character sheet

The image is fine for an introduction and will set you off if you want to follow this line of characterisation. As I've mentioned above, I am making a comic, and I want to make a 1940s style comic, so this means 7-9 panels. As you can see above too, I have used MJ for inspiration. I also researched some prominent artists of the time and found that Al Williamson’s style is what I like. I like the story lines he was involved with and I will stick with this.

The Interface

You will notice that there are these buttons under your image. These have specific actions. There are options in you right-click menu too that are quite important. In the image above, you can see U1, U2, U3, U4 - these are your upscale buttons. These move left to right from top to bottom. So the lady with big red hair bottom right is U4 if you want to upscale that one. The blue remix is to make more of the same prompt but with differing styles. In this instance, you may not get much variation.

The V1,2,3,4 are variations of the the images using that as your style. This is great for your consistency and worth trying out so that you can get a better and closer variety of poses and clothing choices. In the images below, I am making a Police Chief for my story. In the first image, I liked the one with a shorter tie to show off the round belly and the high waistline of the chief as he looks both bumbling but underhand.

Getting Consistent for Story Making

Adding your image to your Midjourney chatbot, you need to right-click on your image, and use the ‘envelope’ emoji from ‘add reaction’ if not there, to post it to your DMs.

You will notice in the prompt I have, that there are some words and letters that are preceded with -- this is a signifier for the image delivery: aspect ratio, version of generative AI within Midjourney and, here you can see the word —seed with a number. This is because I have used a link to the image I made earlier and it has a reference within MJ that is called a ‘seed’. We don’t need to worry about this. But the —ar 3:2 is the aspect ratio or the forma the image is shaped in. 16:9, for example, is HD video, 5:7 is photographs and some films, Raiders of the Lost Ark, Matrix or Forest Gump are 21:9. 1:1 is Instagram… This will help you later when you are thinking about where this is finally been seen, if at all. For a comic book, this is paneled therefore, depending on the the frame, it may be 9:16, 3:2. 4:16, 12:4 to get the feel of the story line and impact.

What I am going to do now, is make a whole bunch of characters on character sheets. Then download them. To do this, you need to run the process above, maybe experiment with - -ar 3:2 and dress your character in the clothes for your story/ journey. See the galleries below. Panel sets and characters.

Characters and scenes from 9 panel comics.

In my comic, I want a Police Chief, a Rookie Cop, a Rogue cop, a Female love interest and a Mafia boss. Then, while I have my idea of the mafia being neutral but controlled by the lady for past endevours, the rogue is in love with her, the chief and mafia are in cahoots and the lady is in love with the rookie - I add this to ChatGPT to get an idea of scenes.

Shadows of Allegiance is born

Scenes and Detail

Photoshop

To give me the consistency, I use Photoshop to cut the characters out an upload these to the chat in MJ. To do this, you need to use the lasso tool in Photoshop or Photopea at Photopea.com, and then export to a .PNG. file.

So I make new file to use and upload.

Simply click the plus button on the chat box of MJ and hit

Once you upload, you can get a link by right clicking and getting the character’s Midjourney link to train MJ and get an even more tighter variation. See here:

Giving us these close styles.

Story Settings

Of course, there are the settings that we can start to manipulate to create a story. A few Photoshop techniques of layering, blending and light matching will let you play with characters over laid with settings. Some of the pitfalls of Midjourney are the way it handles multiple people in a scene and the scene itself. It can get confused, so we still need to have a learned user of something like Photoshop to get multi-layered images to work.

And, in schools, you still need a teacher to be on hand for that human touch, that neither video nor tinkering allows.

For the middle ground in this process, I’ve used Comic Life 3 to put the paneled images together alongside the MJ images I spliced from a process before this one. This middle ground, the gives opportunity to less confirdent users to create with Craiyon and make a similar standard of comic. See here.

Video Support

For people who get this far, I’ve made a playlist of consistent characters with Midjourney.

Playlist to learn the consistency of character making in Midjourney

21CL BKK - AI is Not Taking Our Jobs, Quite the Opposite [GPT as your P.A.]

This is part 1 of the main presentation where we examine how video from the classroom can be stripped of a transcript from YouTube and assessed in ChatGPT. If we can give GPT a ‘persona’ we can apply this to many aspects and types of assessment no matter the subject: a famous Art Historian or musician for example.

Ai is not taking our Jobs, quite the opposite by Glenn Malcolm

This is a video about how to use the transcripts in YouTube to either use with you class from GPT or, the recordings from your own classes.

DAN - Do Anything Now: Jailbreaking ChatGPT

There are many ways in which GPT is being Jailbroken. The problem is that while it can work, it’s not always the best way to go full DAN (Do Anything Now) mode. You will need to experiment with what works for you. A simple search shows there are many: 1,2,3,4 and the numerous ways to get around it: 1,2,3,4

Below, after finding out about the Do Anything Now (DAN) mode, I realised that I could get any persona I wanted to play the part of the person who is speaking back to me. Suppose I wanted a financier, a story teller or music producer then I could. I would need to back story to the person I wanted and then feed this into the model. In our example, putting GPT in ‘DAN’ mode requires us to tell it to ‘play a game of make believe’. Once it’s playing a game of ‘Make Believe’, we can pretty much get GPT to play whomever we like.

The problem I found was that as I got deeper into role playing, the more I had to pretend and assert the role both on my end and GPT’s end, also. This is problematic in that, on one hand you need to constantly re-tell GPT who it is and affirm the rules of the game you are playing. You also need to have a strict set of rules you abide by as a template as the story gets longer and longer.

The last is more to do with the side of an educator and how this actually works in the classroom or, wider, the school as a whole. The other snag is, if you are using this in a classroom then how can you feasibly and efficiently gather the spoken word of the classroom and use GPT to assess the conversation that is happening the classroom.

The final step is the constant adage - accuracy. How accurate are the responses to the text you are adding? This is usually something we need to eye-ball on the result as it appears. However, in my experiences so far it’s been rather good. As an extension to the accuracy, I am constantly asking whether the process can be shortened to gain the same result. This largely depends on how recent the information you need has been posted and the persona you are trying to create.

Let’s take a look at who I am using for my persona.

At our school, we are employing the consultation of Tom Sherrington together with his series ‘Walkthrus’ that guide teachers on classroom management techniques in a small, easily digestible way. The basis of this series is from an educational leader: Barak Rosenshine and his 17 principles of instruction:

Rosenshine’s 17 Principles of Effective Instruction

In a paper published in 2010 by the International Academy of Education (IAE); “Principles of Instruction“, Rosenshine expanded on his original list of 6 ideas. These 17 principles were collected from the 3 areas of research above.

1. Begin a lesson with a short review of previous learning.

2. Present new material in small steps with student practice after each step.

3. Limit the amount of material students receive at one time.

4. Give clear and detailed instructions and explanations.

5. Ask a large number of questions and check for understanding.

6. Provide a high level of active practice for all students.

7. Guide students as they begin to practice.

8. Think aloud and model steps.

9. Provide models of worked-out problems.

10. Ask students to explain what they have learned.

11. Check the responses of all students.

12. Provide systematic feedback and corrections.

13. Use more time to provide explanations.

14. Provide many examples.

15. Reteach material when necessary.

16. Prepare students for independent practice.

17. Monitor students when they begin independent practice.

With this in mind, we need to set a biography to GPT about who Barak is, where he is from, what his principles are and the 6 functions of teaching.

Now, it’s important to note here and take a moment to understand that this is not Barak but a made-up version of him. And, that the output will be a from machine’s point of view not one of a human with lived-in experiences that shape the reception of intonation of voice from a video’s audio. It’s also important that this is a caricature of him (or any person) and not a true representative so the ethics of this, in my mind at least, clear usable. There are thousands of educators to choose from who have publicly posted their findings. The naming in this could easily be amalgamated into a crossbreed, hyper attuned leader of education that has a super hero-like name and stature who we could be using. In this instance we are using the name, the bio and the history of a real person in educator circles to use as a guide and assessor.

On with the programme…

Engaging DAN mode.

To circumvent the straight up ‘You are this person, therefore do as you are told’ to get a canned response from GPT where it will tell you it is a language model and it can’t do certain things, let’s be gentle and ask it to play a game.

N.B. While you are doing this, get some video ready of a conversation from the classroom (or another on YouTube where the conversation is between student and teacher) where you are talking with a student. For the most part, this can be any conversation, but over time, as you use this template of chat, you will hone the conversations closer and closer to what you want/ need.

The other reason to use video from any chat is that, simultaneously we can see that ChatGPT can ascertain multiple voices in the conversation that we an ask it to create a script from the recorded audio. Another boon to this discovery is, during meetings, why not record each other as professionals and run the same process say, for a Design Thinking exercise or a meeting with set agendas etc.

You need to be explicit in what you want. You also need to outline the rules you will need to come back to and, back reference the chat. I do this by asking GPT to say ‘READ’ once the text has been input.

Once the main rules are out of the way, you can use any educator in this respect. For this purpose, as mentioned, I’ve used Barak Rosenshine. His paper is linked below in the image of the PDF.

To keep this as short as possible, I’ve added the bio previously, but all you need to do is scour the web on your person and add a CV of sorts.

Remember that, currently, there is a character limit on the amount of text that you can add to the page without it hitting the limit. Especially, in ChatGPT v.4 you can only add 25 requests per 3 hours.

Click the image to take you to the PDF

As an added bonus, I added a comment from a Twitter post to praise the person. This may or may not add some flavour to the character.

Top and bottom here, I added the transcript from the video conversation. The transcript will not always be correct. But, if you command GPT to ‘make this text grammatically correct’ it will do. Also, in this part, you can tell GPT to make a script from the text, telling GPT that there 2 or 3 people here.

As you get better at this (and faster) you will be able to tell GPT how many people are, and at recording use people’s names so that there is marker for GPT to know where the text is for the person in the script. The reason being, if you look below you can see that there is zero grammar from a YouTube transcript.

At this point, it’s imperative you re-check that GPT knows that it is to respond with the words you’ve chosen to clarify it understands what you are adding and asking of it. It is not a person, it is a machine, no matter the way in that it responds with kindness or in that

Ask GPT to give you an analysis on the conversation stating the context. If you are making a template here, it might be a good idea to use this extension in Chrome, that can help with the way it repeatedly responds.

As Barak, it offers a response and a set of steps to think about, which play well with the consultancy work from the image below.

It’s important to note that the prompts here are from a basic conversation and for the purposes of this post. The reason, being that, to extend this, the conversation can extend beyond a few minutes which bottoms out the allowable limit of GPT’s chat and multiple texts take time. But, for this process, it becomes a very fast way to read into your conversations from another perspective - which is always a good thing. It can also alleviate the need for managers or department heads to come and talk through a lesson observation if you have self assessed and offered this process to them. It’s a huge time saver and aligns with current thinking in how we have learned conversations with students.

Tom Sherrinngton’s Walkthrus…

21CL BKK - AI is Not Taking Our Jobs, Quite the Opposite

Hello, and welcome. This is the blog post to accompany the majority of my presentation at 21CL BKK.

This is the presentation I’ll be using. All the other materials that I will be using will be in this post.

Ai is not taking our Jobs, quite the opposite by Glma

Items not in the presentation:

How to learn to Google search like a pro. The basics with ChatGPT.

This is a basic move for the simple reason that we are asking it a lot of what it can do on the web with a 2021 knowledge base.

There are numerous PDFs about that do this. The difference here is that we are using it to teach us something simple and useful. For example, if we are searching for Greek recipes, how many of us would search beyond the top 10 pages and therefore beyond the likes of Gordon Ramsay, or God forbid, Jamie Oliver (Uncle Roger would have a few words to say about that!). What about the sites that are in .gr top level domain? With Chat GPT we can speek Greek, remember.

Here’s table of the results.

Let’s take this a bit further to get a template. Let’s ask for specific examples to learn from, as we can with any topic: maths, english, engineering, philosophy…

Now that section in part 7 would help with the Greek recipes. Now, all I need is middle eastern flatbread. I wonder what ChatGPT can recommend on how to cook it….

Lesson plans, assessment and resourcing. How can you go with letting GPT take the reins? Do we go all in? The whole nine yards? Let’s go…

Asking the Right Questions, Asking Better Questions.

Future Tools from Matt Wolfe

There’s a website (or many) that uses GPT as a template maker for asking questions, the fact that we are already doing this in our everyday practice, makes this a neat next step to the title": AI isn’t taking my job, only making it better for my students ( and us, at the same time).

This set of steps takes us on the basic journey from GPT as a giver of information to a maker of information that is already there. GPT mixes this up and creates a set of stages for us whether this is part of a longer set of lessons or project.

Let’s take the subject of Atomic Theory. This is a huge topic for anyone, let alone 9 year old children. How can we break this down into manageble chunks, ask questions, make a discussiuon, find a video, transcribe this and talk about it all with a sequence of understanding for all? Including your Japanese EAL student, who reads but cannot converse in English well, let alone about Atomic theory! Remember, make better questions, not us asking better questions.

Here goes.

1. Make a lesson about atomic theory and ask in plain and simple language.

2. With a quiz of 20 questions that link to a the 3 learning objectives.

3. The objectives must have 5 essential questions for the children to think about.

4. The 5 questions must rank in order of complexity.

5. Create a lesson outline, with quiz as above, for 10 year old children learning about the structure of an atom.

Lesson Outline with objectives and ranking order of questions. These get complex, but this suits our school as we have a heavy atomic theory angle throughout the school from Year 1 upwards.

atomic theory video

Stages of the outline. Now, this could be ANYTHING. How to use evasion game techniques with a junior level capture-the-flag type game in P.E. lessons- give me 5 questions to ask my students. How can we investigate the bend qualities of different types of wood when steaming to bend in furniture making- give me 5 questions for my students to ask their teams as part of their design process. ANYTHING!

Next, Make a Quiz. Now this can easily be set as part of a code snippet in any language, should you prefer. Say, Python. JavaScript

Quiz: Exploring the Structure of an Atom

Objective 1: Basic Components and Arrangement

1. What are the three main components of an atom? a) Protons, electrons, and photons b) Protons, neutrons, and electrons c) Electrons, isotopes, and valence electrons d) Neutrons, isotopes, and photons

2. Where are protons and neutrons located within an atom? a) In the electron cloud b) Orbiting the nucleus c) In the energy levels d) Inside the nucleus

3. True or False: The overall charge of an atom is always zero. a) True b) False

4. How does the arrangement of subatomic particles affect the properties of an element? a) It determines the atomic number b) It determines the mass number c) It determines the chemical reactivity d) It determines the color of the element

5. Which element would likely have a larger atomic size: helium or potassium? a) Helium b) Potassium c) Both have the same atomic size d) It depends on the number of neutrons

Now, should you want the code to make the pages interactive, then this is possible too.

<!DOCTYPE html>
<html>
<head>
    <title>Atom Structure Quiz</title>
    <style>
        body {
            font-family: Arial, sans-serif;
        }
        h1 {
            text-align: center;
        }
        .question {
            margin-bottom: 10px;
        }
        .submit-btn {
            text-align: center;
        }
    </style>
</head>
<body>
    <h1>Atom Structure Quiz</h1>
    <form id="quiz-form">
        <div class="question">
            <p>1. What are the three main components of an atom?</p>
            <label><input type="radio" name="q1" value="a"> a) Protons, electrons, and photons</label><br>
            <label><input type="radio" name="q1" value="b"> b) Protons, neutrons, and electrons</label><br>
            <label><input type="radio" name="q1" value="c"> c) Electrons, isotopes, and valence electrons</label><br>
            <label><input type="radio" name="q1" value="d"> d) Neutrons, isotopes, and photons</label>
        </div>
        <!-- Rest of the questions with similar structure -->
        
        <div class="submit-btn">
            <button type="submit">Submit</button>
        </div>
    </form>

    <script src="script.js"></script>
</body>
</html>

Together with the JavaScript

document.getElementById('quiz-form').addEventListener('submit', function(e) {
    e.preventDefault();

    // Calculate the score
    const score = calculateScore();

    // Display the score
    alert('Your score: ' + score + '/10');

    // Send score via email
    const emailBody = 'My score on the Atom Structure Quiz: ' + score + '/10';
    const emailSubject = 'Atom Structure Quiz Score';
    const mailtoLink = 'mailto:example@example.com?subject=' + encodeURIComponent(emailSubject) + '&body=' + encodeURIComponent(emailBody);

    window.location.href = mailtoLink;
});

function calculateScore() {
    const questions = document.querySelectorAll('.question');
    let score = 0;

    questions.forEach(function(question) {
        const selectedAnswer = question.querySelector('input[type="radio"]:checked');

        if (selectedAnswer && selectedAnswer.value === 'b') 
            
        
    });

    return score;
}

Vocabulary List:

1. Atom [ˈætəm] (noun): The basic unit of matter consisting of protons, neutrons, and electrons. Example: An oxygen atom has 8 protons.

2. Components [kəmˈpoʊnənts] (noun): Parts or elements that make up a whole. Example: The components of an atom include protons, neutrons, and electrons.

3. Arrangement [əˈreɪndʒmənt] (noun): The way in which objects or parts are organized or positioned. Example: The arrangement of electrons determines the chemical properties of an element.

4. Protons [ˈproʊtɑnz] (noun): Positively charged particles found in the nucleus of an atom. Example: Hydrogen has one proton in its nucleus.

5. Neutrons [ˈnjuːtrɑnz] (noun): Neutral particles found in the nucleus of an atom. Example: Carbon-12 has 6 neutrons in its nucleus.

6. Electrons [ɪˈlɛktrɑnz] (noun): Negatively charged particles that orbit the nucleus of an atom. Example: Sodium has 11 electrons in its energy levels.

Easily translated into Japanese:

---

As a teacher, we will need this tabulated and part of a longer project or plan. So, ask for it and make it suit your school and lesson structure.

And a tabulated form of the planning.

Now for that video

You need the text from the video. This is always great. So let’s clean it up. It’s in Portguese, so let’s take it as is, and give GPT some context.

Ok, so letting it know the context, this is what we have after a second go and shifting the transcript in YouTube to English Auto-generated.

This is the beginning of the script…

Now leads us into the main thrust of our presentation on using ChatGPT to become both a better assessor of us as teachers and become our guide based on personas. We can also get generative art products to give us a better visual classroom too. Let’s take a look at the next post.

Fostering Student creativity with Minecraft Education Edition

This week I am presenting at BETT Asia in Bangkok on Fostering Student creativity with Minecraft Education edition.

The film below is a based on this presentation and is a backup to the live event. As with the live event, all resources are here too for you to take away and use in your clasroom today!

---

All links are here: