<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:webfeeds="http://webfeeds.org/rss/1.0">
    <channel>
        <title><![CDATA[Good Future Foundation Community]]></title>
        <description><![CDATA[Good Future Foundation Community]]></description>
        <link>https://community.goodfuture.foundation</link>
        <generator>Bettermode RSS Generator</generator>
        <lastBuildDate>Tue, 17 Nov 2026 03:36:57 GMT</lastBuildDate>
        <atom:link href="https://community.goodfuture.foundation/rss/feed" rel="self" type="application/rss+xml"/>
        <pubDate>Tue, 17 Nov 2026 03:36:57 GMT</pubDate>
        <copyright><![CDATA[2026 Good Future Foundation Community]]></copyright>
        <language><![CDATA[en-US]]></language>
        <ttl>60</ttl>
        <webfeeds:icon></webfeeds:icon>
        <webfeeds:related layout="card" target="browser"/>
        <item>
            <title><![CDATA[Subject-specific AI literacy strategy - a template]]></title>
            <description><![CDATA[https://docs.google.com/document/d/1-Ys2p3sykGHiZIYCwsza5BQ__jfNF-I0iZJYzy2I3Ws/edit?usp=drivesdk [https://docs.google.com/document/d/1-Ys2p3sykGHiZIYCwsza5BQ__jfNF-I0iZJYzy2I3Ws/edit?usp=drivesdk]



]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/subject-specific-ai-literacy-strategy---a-template-rEFjuhziDn0DDrb</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/subject-specific-ai-literacy-strategy---a-template-rEFjuhziDn0DDrb</guid>
            <category><![CDATA[AI Literacy]]></category>
            <category><![CDATA[CPD]]></category>
            <category><![CDATA[curriculum]]></category>
            <category><![CDATA[Secondary]]></category>
            <category><![CDATA[strategy]]></category>
            <dc:creator><![CDATA[Madeleine Champagnie]]></dc:creator>
            <pubDate>Fri, 16 Oct 2026 06:42:40 GMT</pubDate>
            <content:encoded><![CDATA[<p><a href="https://docs.google.com/document/d/1-Ys2p3sykGHiZIYCwsza5BQ__jfNF-I0iZJYzy2I3Ws/edit?usp=drivesdk" rel="noopener noreferrer nofollow" class="text-interactive hover:text-interactive-hovered">https://docs.google.com/document/d/1-Ys2p3sykGHiZIYCwsza5BQ__jfNF-I0iZJYzy2I3Ws/edit?usp=drivesdk</a></p><div data-type="embed" data-id="9GxZOyPlUmYkMwMtofUeE" data-embed-url="https://docs.google.com/document/d/1-Ys2p3sykGHiZIYCwsza5BQ__jfNF-I0iZJYzy2I3Ws/edit?usp=drivesdk"></div><p></p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Using AI to Plan, Teach, and Reflect - Custom Copilot Agent Transforms Lesson Design at GEMS Winchester School, Dubai]]></title>
            <description><![CDATA[In Short:

 * Teachers use a custom Copilot agent to design lessons aligned with cognitive science

 * Using AI to strengthen instructional precision, reduce admin burden, and embed
   
   evidence-based teaching ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/using-ai-to-plan-teach-and-reflect---custom-copilot-agent-transforms-5V1dcMUEadXSmGJ</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/using-ai-to-plan-teach-and-reflect---custom-copilot-agent-transforms-5V1dcMUEadXSmGJ</guid>
            <category><![CDATA[Primary]]></category>
            <category><![CDATA[Secondary]]></category>
            <dc:creator><![CDATA[Info Good Future Foundation]]></dc:creator>
            <pubDate>Thu, 04 Dec 2025 11:38:40 GMT</pubDate>
            <content:encoded><![CDATA[<figure data-align="center" data-size="half" data-id="ZeBq3aC52lmWddS062iIf" data-version="v2" data-type="image"><img data-id="ZeBq3aC52lmWddS062iIf" src="https://tribe-s3-production.imgix.net/ZeBq3aC52lmWddS062iIf?auto=compress,format"></figure><p><strong>In Short:</strong></p><ul><li><p>Teachers use a <strong>custom Copilot agent</strong> to design lessons aligned with cognitive science</p></li><li><p>Using AI to strengthen instructional precision, reduce admin burden, and embed</p><p>evidence-based teaching techniques</p></li><li><p>Apply <strong>Willingham’s Memory model, Rosenshine’s</strong> Principles of instruction, retrieval Practice, Cognitive science systematically</p></li><li><p>Reflect on how AI amplifies teacher expertise without replacing pedagogical judgment</p></li></ul><figure data-align="center" data-size="half" data-id="vv274wBrX2D3QSU1CtRxY" data-version="v2" data-type="image"><img data-id="vv274wBrX2D3QSU1CtRxY" src="https://tribe-s3-production.imgix.net/vv274wBrX2D3QSU1CtRxY?auto=compress,format"></figure><figure data-align="center" data-size="best-fit" data-id="17dYO6W9j8oUORkkZKuwy" data-version="v2" data-type="image"><img data-id="17dYO6W9j8oUORkkZKuwy" src="https://tribe-s3-production.imgix.net/17dYO6W9j8oUORkkZKuwy?auto=compress,format"></figure><p></p><p>At GEMS Winchester School, we are innovating how lesson planning looks in an AI age. Our teachers have been using a custom Copilot agent, a purpose-built tool that transforms how educators design instruction and embed the science of learning into daily practice. This AI agent is structured around Daniel Willingham’s cognitive principles and Doug Lemov’s proven classroom techniques, which our school has adapted into our planning and delivery model. With intelligent prompting, teachers turn every planning session into an opportunity to develop essential instructional skills: precision, consistency, differentiation, and reflection. The agent guides teachers through every stage of lesson design, helping them move from “filling in a template” to “thinking pedagogically through.” Teachers hence use AI to deepen instructional quality and practice deliberate planning.<br><br><strong>From Theory to Practice: How It Looks in the Classroom</strong></p><figure data-align="center" data-size="best-fit" data-id="DoEbHkglCo2UXIsXi6ind" data-version="v2" data-type="image"><img data-id="DoEbHkglCo2UXIsXi6ind" src="https://tribe-s3-production.imgix.net/DoEbHkglCo2UXIsXi6ind?auto=compress,format"></figure><figure data-align="center" data-size="best-fit" data-id="cCsq1hlnRD69SxNmmobVz" data-version="v2" data-type="image"><img data-id="cCsq1hlnRD69SxNmmobVz" src="https://tribe-s3-production.imgix.net/cCsq1hlnRD69SxNmmobVz?auto=compress,format"></figure><p>Teachers explored the AI agent across several planning scenarios:</p><p><strong>Curriculum-Aligned Outcomes:</strong> Inputting year group and topic (e.g., “Year 6 Circulatory system”) and receiving pre-generated learning outcomes focusing on procedural knowledge or skills to be gained and “To Know” essentials that are factual or conceptual knowledge components aligned with our curriculum standards.</p><p><strong>Technique Integration:</strong> The agent suggests specific Lemov’s techniques at strategic points (e.g., “Use Cold Call after explaining mitochondria function to ensure all students are processing the concept”).</p><p><strong>Cognitive Load Management:</strong> Lessons are automatically structured to avoid working memory overload, with content chunked appropriately and retrieval practice embedded at intervals.</p><p><strong>Generating feedback comments: </strong>Copilot agent creates feedback comments that help students correct and improve their responses and suggest a follow up challenge question.</p><p>Each activity reinforced the same core idea: better planning leads to better teaching, and better teaching leads to better learning outcomes. Teachers use P.R.O.M.P.T :<strong> (Precise, Role-Based, Outcome-Oriented, Medium-Specific, Provide Context, Test &amp; Refine</strong> ) framework to query custom copilot agent. A pre - designed prompt bank is developed and integrated with copilot agent to support teachers with using the agent.</p><p><strong>Real Teacher Scenarios: Before &amp; After Using the Agent</strong></p><figure data-align="center" data-size="best-fit" data-id="6OeQhs8m05KkrJm7Ya9F8" data-version="v2" data-type="image"><img data-id="6OeQhs8m05KkrJm7Ya9F8" src="https://tribe-s3-production.imgix.net/6OeQhs8m05KkrJm7Ya9F8?auto=compress,format"></figure><p>After using the agent, teachers quickly noticed how AI-embedded cognitive science transformed their instruction from generic to <em>genuinely impactful</em>.</p><p><strong>Metacognition Moments</strong></p><p>Reflecting after implementation, teachers shared insights about their planning process, what we call <strong>Metacognition Moments</strong>:</p><p>“I realized my original lessons weren’t strategically checking for understanding. The agent showed me where to pause and assess, not just at the end.”</p><p>“When I use the Copilot agent, my lessons feel impactful. It’s like having an instructional coach reminding me why each component matters.”</p><p>“Seeing Lemov techniques embedded in context helped me understand <em>when</em> to use them, not just <em>what</em> they are.”</p><p>These reflections align beautifully with WSD’s commitment to evidence-based teaching, purposeful AI integration for learning &amp; teaching and embedding the <em>science behind instruction</em> into every planning session.</p><h3 class="text-lg" data-toc-id="179b6db4-6e4b-45c5-8e2b-1faa76e227b5" id="179b6db4-6e4b-45c5-8e2b-1faa76e227b5"><strong>Why a Custom Copilot Agent Matters?</strong></h3><p>Emerging research tells us that AI integration in education is not just a nice-to-have—it’s transformative when purpose-built. Generic Most AI tools lack pedagogical grounding, but custom agents trained on specific instructional models can systematically apply what we know works. Our agent embeds:</p><ul><li><p><strong>Willingham’s cognitive principles:</strong> Lessons are designed to activate prior knowledge, manage working memory, and promote long-term retention through spaced retrieval.</p></li><li><p><strong>Lemov’s techniques:</strong> Strategic deployment of Cold Call, Check for Understanding, Ratio, and other high-leverage moves at optimal moments.</p></li><li><p><strong>School-specific adaptations:</strong> Our refined approaches to adaptive teaching, assessment, and curriculum sequencing.</p></li></ul><p>In our whole-school instructional program, we emphasize the cycle of <em>plan → teach → reflect → refine</em>. Using AI in planning mirrors that cycle: teachers review agent output, personalize for their students, teach the lesson, and reflect on effectiveness. So, the Copilot agent becomes an extension of professional development, not a separate add-on.</p><p><strong>The Benefits: Time, Precision, and Growth</strong></p><p><strong>Time Savings:</strong> What once took 45 minutes now takes 10. Teachers review, adjust, and personalize rather than building from scratch.</p><p><strong>Instructional Consistency:</strong> Every teacher, regardless of experience, plans lessons rooted in cognitive science and proven techniques.</p><p><strong>Reduced Cognitive Load for Teachers:</strong> With planning streamlined, teachers have bandwidth for responsive teaching, the real-time adjustments that no AI can predict.</p><p><strong>Continuous Professional Learning:</strong> Teachers see exemplar planning daily, internalizing the science of learning through repeated exposure.</p><p><strong>Focus on art of teaching:</strong> By handling structural rigor, the agent frees teachers to focus on relationships, culture-building, and in-the-moment pedagogical decisions.</p><p><strong>Looking Ahead</strong></p><p>Going ahead, teachers will extend their use of the Copilot agent across subjects from science to humanities to languages, applying evidence-based strategies in every lesson they design. At GEMS Winchester School, purposeful and pedagogically grounded AI drives our approach to innovation. We are guiding teachers to <em>plan with intention</em>, integrating AI carefully and strategically into the heart of meaningful instruction. Leaders ensure AI enhances teaching with purpose, precision, and reflection; never replacing teacher expertise, always amplifying it.</p><p><strong>References</strong></p><ul><li><p>Willingham, D. T. (2009). <em>Why Don’t Students Like School? A Cognitive Scientist Answers Questions About How the Mind Works and What It Means for the Classroom.</em> Jossey-Bass.</p></li><li><p>Lemov, D. (2015). <em>Teach Like a Champion 2.0: 62 Techniques That Put Students on the Path to College.</em> Jossey-Bass.</p></li><li><p>Zawacki-Richter, O., &amp; Anderson, T. (2025). <em>AI Integration in Educational Practice: Implications for Teacher Planning.</em> Educational Technology Review, SpringerOpen.<br><br></p><figure data-align="center" data-size="best-fit" data-id="afghSiA9esJM2ShvDwNfq" data-version="v2" data-type="image"><img data-id="afghSiA9esJM2ShvDwNfq" src="https://tribe-s3-production.imgix.net/afghSiA9esJM2ShvDwNfq?auto=compress,format"></figure></li></ul>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Vibe-Coding Mini-Games: Teaching Prompt Engineering by Making Something Students Want to Play]]></title>
            <description><![CDATA[Lesson Flow

Vibe-coding is a new approach of AI-first software development, where instead of learning to code through programming languages, the student uses conversational language to instruct the AI ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/vibe-coding-mini-games-teaching-prompt-engineering-by-making-something-CarZQktAqCRSTkJ</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/vibe-coding-mini-games-teaching-prompt-engineering-by-making-something-CarZQktAqCRSTkJ</guid>
            <category><![CDATA[Secondary]]></category>
            <dc:creator><![CDATA[Joseph Lin]]></dc:creator>
            <pubDate>Tue, 16 Sep 2025 14:22:28 GMT</pubDate>
            <content:encoded><![CDATA[<p><strong>Lesson Flow</strong></p><p>Vibe-coding is a new approach of AI-first software development, where instead of learning to code through programming languages, the student uses conversational language to instruct the AI to create a program for them. It abstracts away the complexity of programming, and replaces it with plain English communication about what problem the software aims to solve, how the app should look and feel, the way users are meant to use it, and the results are often surprising and delightful.</p><ol><li><p><strong>Introduce vibe coding</strong></p><p>We opened with Andrej Karpathy’s legendary quote that “The hottest new programming language is English”, and made the point that being an OpenAI co-founder and the former director of AI at Tesla, he is making an informed and profound point about the future of software development. To drive the point home, we played a short video about Canva’s new AI coding feature to set expectations and energy.</p></li><li><p><strong>Students learn:</strong></p><ul><li><p>Motivation first: when the outcome is fun and personal, attention to detail follows naturally.</p></li><li><p>AI is a <strong>tool</strong>, not a magician; quality depends on the clarity of your request</p><p></p><div data-embed-url="https://youtu.be/RnVsl3PIx8U" data-id="a6Z8XSmh2TGRbI8U8fuaW" data-type="embed"></div></li></ul></li><li><p><strong>Know what you want</strong></p><p>Students chose a <strong>tiny, achievable</strong> concept (e.g., <a class="text-interactive hover:text-interactive-hovered" rel="nofollow ugc noopener" href="https://cookieclicker.com/"><u>cookie clicker</u></a> game, solar system visualiser, two-player Snake, tic-tac-toe on a 4x4 board, etc.), and had to write a short spec for what they’d like to build:</p><p><br></p><figure data-align="center" data-size="best-fit" data-id="26E4rpGpjTZaZVzsIyNuF" data-version="v2" data-type="image"><img data-id="26E4rpGpjTZaZVzsIyNuF" src="https://tribe-s3-production.imgix.net/26E4rpGpjTZaZVzsIyNuF?auto=compress,format"></figure></li><li><p>After answering these short questions, they share it with their neighbour to make sure others can actually understand what they’d like to build.</p><p><strong>Students learn:</strong></p><ul><li><p><strong>GIGO</strong> in practice: Telling AI to “<em>make a game for me</em>” will yield unwanted results; “<em>a two-player game of snake controlled by the arrow keys and WASD keys, in retro style, where both players control a snake chasing after the same apple</em>” is buildable.</p></li><li><p>How to use descriptive language to make their concept tangible and understandable - if your friend cannot understand you, the AI probably won’t either.</p></li></ul></li><li><p><strong>Draft → Generate v1 with AI</strong><br>Students used a chatbot to expand their game specifications into a detailed prompt, which could be entered into Canva Code to generate a first draft. We modelled a prompt scaffold, then let them adapt it.</p></li></ol><figure data-align="center" data-size="best-fit" data-id="goXYjbzjdCfzRlW9e0fQ3" data-version="v2" data-type="image"><img data-id="goXYjbzjdCfzRlW9e0fQ3" src="https://substackcdn.com/image/fetch/$s_!5cLw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff02f01aa-df29-4481-9b28-2f1af8a79c22_2101x2934.png"></figure><ol start="3"><li><p><strong>Students learn:</strong></p><ul><li><p><strong>Use AI to control AI:</strong> if they don’t know how to create a detailed specification, the AI can help them.</p></li></ul></li><li><p><strong>Test like a skeptic, then iterate</strong><br>Pairs tried to <strong>break</strong> each game and write a list of changes they wish to make. Those wishes then had to be rewritten into specific and actional prompts for the AI to fix.</p></li></ol><figure data-align="center" data-size="best-fit" data-id="lAuNihAxkWYxFt3naHTCP" data-version="v2" data-type="image"><img data-id="lAuNihAxkWYxFt3naHTCP" src="https://substackcdn.com/image/fetch/$s_!ehgG!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F95a3d7b9-57e5-42ae-b038-dd7de3e67c99_1908x2650.png"></figure><ol start="3"><li><p><strong>Students learn:</strong></p><ul><li><p>Iteration beats inspiration: small, boring improvements compound.</p></li><li><p>Feedback should be specific and actionable.</p></li></ul></li><li><p><strong>Gallery walk and reflection</strong></p><p>Students had 30 minutes to iterate and then they had to set up their games for others to play. After playing someone’s game, they had to leave one praise and one suggestion (all specific and actionable of course).</p><p>As a wrap up, the teacher made an explicit connection between what they learned today to how they should be using AI: have a clear vision about what you want, give clear instructions, and keep iterating.</p><p>Play the game yourself!</p></li></ol><figure data-align="center" data-size="best-fit" data-id="z2L6hqoHQJeYr6LAsk5yj" data-version="v2" data-type="image"><img data-id="z2L6hqoHQJeYr6LAsk5yj" src="https://substackcdn.com/image/fetch/$s_!EUZA!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe434b6a7-07db-4b6d-9fee-043020fc87e0_1003x1401.png"></figure><ol start="3"><li><p><strong>Students learn:</strong></p><ul><li><p>Clarity and accessibility are part of “done”, not extras.</p></li><li><p>Shipping creates accountability; a playable link focuses attention.</p></li></ul></li></ol><p><strong>Conclusion</strong><br>When brainstorming with the school, the teacher originally wanted students to learn coding from scratch because they wanted the students to have strong fundamentals in traditional coding before introducing them to AI coding tools. That idea soon went out the window once the teacher realised how steep the learning curve would be. I think it was good prioritisation to first enthuse students by showing them what they can accomplish, before deepening their learning by going back to the fundamentals. The bigger win, though, was mindset: students moved from “tell the AI to make a game” to <strong>specifying, testing, and refining</strong>—skills they can carry into essays, research notes, slide decks, and beyond.</p><p></p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Practical Example of AI for Debate Preparation]]></title>
            <description><![CDATA[In Short:

 * Analog first, AI second. A quick chalkboard mind-map grounds definitions and strategy before any screen lights up.

 * Tech as an accelerator, not a crutch. AI speeds the process while keeping ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/practical-example-of-ai-for-debate-preparation-TpxKkZ7dFFMMVi8</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/practical-example-of-ai-for-debate-preparation-TpxKkZ7dFFMMVi8</guid>
            <dc:creator><![CDATA[Joseph Lin]]></dc:creator>
            <pubDate>Tue, 01 Jul 2025 15:31:13 GMT</pubDate>
            <content:encoded><![CDATA[<p><strong>In Short:</strong></p><ul><li><p><strong>Analog first, AI second. </strong>A quick chalkboard mind-map grounds definitions and strategy before any screen lights up.</p></li><li><p><strong>Tech as an accelerator, not a crutch. AI speeds the process while keeping performance and real-time thinking squarely in students’ hands.</strong></p></li></ul><figure data-align="center" data-size="half" data-id="AQWlKCClNk8EjCuF4H0kS" data-version="v2" data-type="image"><img data-id="AQWlKCClNk8EjCuF4H0kS" src="https://substackcdn.com/image/fetch/$s_!LhnH!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8a8a4197-cde4-46dd-8d14-96b4519535b3_2800x240.png"></figure><p>Faced with the motion <strong>“Is learning English still relevant in Hong Kong today?”</strong> a secondary debate team skipped the usual scatter-shot Googling and trialled a lean AI workflow. One brisk session—analog brainstorm, targeted deep research, auto-outlining, and text-to-speech rehearsal—produced draft speeches for every speaker. By shifting grunt work to machines, students spent their energy on strategy, rebuttals, and stagecraft.</p><p><strong>How It Worked</strong></p><figure data-align="center" data-size="half" data-id="DePPiNPvZwmrxXSxrE619" data-version="v2" data-type="image"><img data-id="DePPiNPvZwmrxXSxrE619" src="https://substackcdn.com/image/fetch/$s_!ZM8F!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6995ca6a-768f-4112-a6ed-73224ad16412_793x153.png"></figure><p><strong>Activity: </strong>Team huddled around a chalkboard, unpacking definitions, burdens, and stakeholders. Phones stayed in pockets; a quick photo became the plan.</p><p><strong><em>No AI</em></strong></p><figure data-align="center" data-size="half" data-id="PdjowwdPDtmcmCjzngpQZ" data-version="v2" data-type="image"><img data-id="PdjowwdPDtmcmCjzngpQZ" src="https://substackcdn.com/image/fetch/$s_!SG7M!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe93656c5-9977-48cb-8a2d-8e70bd93e191_950x154.png"></figure><p><strong>Activity: </strong>Pairs spent 15 minutes with <strong>Perplexity Research Mode</strong> and <strong>Gemini</strong> <strong>Deep Research </strong>to surface statistics, expert quotes, and counter-examples. Each pair shared 1-2 key findings with the team.</p><p><strong>Prompt: </strong>“You are a research assistant for a school debate. Motion: <em>Is learning English still relevant in Hong Kong today?</em> 1. List the three strongest claims <strong>for</strong> and <strong>against</strong> (≤40 words each). 2. Provide three credible sources per claim (title, year, link). 3.Flag key rebuttals. Return as a table.”</p><figure data-align="center" data-size="half" data-id="2nYh0UhDqeiQsAr2mV6mF" data-version="v2" data-type="image"><img data-id="2nYh0UhDqeiQsAr2mV6mF" src="https://substackcdn.com/image/fetch/$s_!q9Su!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faf3f8f32-18f6-4200-86a2-0c67f0c7c1f6_793x154.png"></figure><p><strong>Activity: </strong>A Voice Memo captured a 20-minute strategy discussion. Their discussion was transcribed and then organized into a clear outline. Breaking down who will talk about which points using which evidence and what questions they can raise.</p><p><strong>Prompt: </strong>“Turn this transcript into a concise outline: headings = argument, bullets = supporting evidence, note any action items.”</p><figure data-align="center" data-size="half" data-id="AOY9sWQbrWFWRmKrMDezy" data-version="v2" data-type="image"><img data-id="AOY9sWQbrWFWRmKrMDezy" src="https://substackcdn.com/image/fetch/$s_!heHf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faaae379b-b441-45c3-991a-e5bf8f8e6928_793x153.png"></figure><p><strong>Activity: </strong>Each speaker merged the outline and evidence into a 4-minute script inside ChatGPT. They had to read it out to themselves and edit it (with AI or otherwise) so that it is easy and smooth for them to read out loud.</p><p><strong>Prompt: </strong>“Draft a persuasive debate speech using our outline. Clear signposting, conversational tone, memorable closing line. Keep it under four minutes.”</p><p>“I added this speech to use simpler language. I prefer shorter sentences and repetition of these keywords…”</p><figure data-align="center" data-size="half" data-id="VPaBCoHL9QvDcpDDU4sSK" data-version="v2" data-type="image"><img data-id="VPaBCoHL9QvDcpDDU4sSK" src="https://substackcdn.com/image/fetch/$s_!pcFJ!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F90ad8d9e-0d6d-4417-ad2d-f9347f6bee53_532x153.png"></figure><p><strong>Activity: </strong>I demoed <a class="text-interactive hover:text-interactive-hovered" rel="noopener noreferrer nofollow" href="http://OpenAI.fm"><strong>OpenAI.fm</strong></a> to show how text-to-speech playback can highlight pacing, stress, and pronunciation; students later used it for individual practice.</p><p><strong><em>(Tool only)</em></strong></p><figure data-align="center" data-size="half" data-id="FnoBW8Jz7gPZNrX6Wvs3a" data-version="v2" data-type="image"><img data-id="FnoBW8Jz7gPZNrX6Wvs3a" src="https://substackcdn.com/image/fetch/$s_!LhnH!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8a8a4197-cde4-46dd-8d14-96b4519535b3_2800x240.png"></figure><p><strong>Impact</strong></p><blockquote><p><em>“We went from blank page to a first-draft speech in one meeting. That never happens.”</em><br><em>“Because an AI note-taker had our backs, we could focus on testing arguments instead of scribbling minutes.”</em></p></blockquote><p>As a coach, I loved that the usual “Who’s got evidence for…?” scramble was much diminished; AI-generated evidence tables were instantly available, and made students feel more secure and equipped to speak out. Freed from procedural clutter such as formatting and diarising, the group spent its energy poking holes in each other’s logic and rehearsing delivery. Rapid progress raised engagement—students left buzzing, eager to refine rather than start over.</p><p></p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI Coding: No Coding Required!]]></title>
            <description><![CDATA[One of my favorite recent studies [https://www.tandfonline.com/doi/full/10.1080/10494820.2025.2457351] examined ChatGPT and plagiarism in Spain. The authors found that “a higher frequency of using ChatGPT for academic purposes does not necessarily lead to a higher ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/ai-coding-no-coding-required-z2hfLV4XNHvhWpG</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/ai-coding-no-coding-required-z2hfLV4XNHvhWpG</guid>
            <dc:creator><![CDATA[Joseph Lin]]></dc:creator>
            <pubDate>Wed, 11 Jun 2025 14:11:46 GMT</pubDate>
            <content:encoded><![CDATA[<p>One of my <a href="https://www.tandfonline.com/doi/full/10.1080/10494820.2025.2457351" rel="nofollow ugc noopener" class="text-interactive hover:text-interactive-hovered"><u>favorite recent studies</u></a> examined ChatGPT and plagiarism in Spain. The authors found that “a higher frequency of using ChatGPT for academic purposes <strong>does not necessarily lead to a higher likelihood of plagiarism</strong>,” instead it is “certain personal variables…such as <strong>being involved in a cheating culture or experiencing amotivation</strong>, that cause the likelihood of plagiarism to increase.”</p><p>I love this conclusion because it means teachers have a powerful role to play, to influence students to use their newfound AI empowerment for good. The challenge lies in creating a school culture that promotes <a href="https://www.pewresearch.org/internet/2023/02/24/the-future-of-human-agency/" rel="nofollow ugc noopener" class="text-interactive hover:text-interactive-hovered"><u>agency</u></a>, integrity, and empathy; furthermore, as more and more of knowledge acquisition is done through AI tutors, there is a strong case to be made that enculturation will become the <a href="https://ccsenet.org/journal/index.php/ies/article/view/0/47519" rel="nofollow ugc noopener" class="text-interactive hover:text-interactive-hovered"><u>most important contribution</u></a> of education to society.</p><p>A very direct way to do so is to teach students to build something that supports Sustainable Development Goals. This has been a typical assignment at the undergraduate level, but GenAI assistance has made it feasible for secondary students to try their hands at similar problem-based and project-based learning. Here’s a course I’m currently piloting, which uses AI to help non-coders create local SDG solutions.<br><br><strong>Overview</strong></p><ul><li><p>Course Theme: AI Coding x Sustainability Solutions</p></li><li><p>Grade: Form 3-5</p></li><li><p>Teacher/TA/student ratio: 1 vs. 3 vs. 30</p></li><li><p>Duration: 24 hours</p></li></ul><p><strong>How It Went Down</strong></p><p>This course is essentially a design thinking course, except everything is sped up because a lot of the work is done by AI. Nevertheless, students have to understand and synthesise information in order to deliver their presentation: the tasks are complex enough and spread across several AIs, that they cannot just prompt the AI once and hand in something AI-generated.</p><figure data-type="image" data-version="v2" data-id="KaJiPhONCsRq1N2rUSWCJ" data-size="best-fit" data-align="center"><img src="https://tribe-s3-production.imgix.net/KaJiPhONCsRq1N2rUSWCJ?auto=compress,format" data-id="KaJiPhONCsRq1N2rUSWCJ"></figure><p><strong>What Students Built</strong></p><p>The course’s learning focus isn’t really the coding, rather it is the skill or mindset of using AI to study a problem, think of solutions, then turning them into reality. The primary assessment criteria is in how well they explain and justify their ideas, followed by how well their solutions work.</p><p>Here are some ideas that the students had:</p><p><strong>SDG 3: Ensure healthy lives and promote well-being for all at all ages</strong></p><ul><li><p>An AI menu analyzer to help people choose low-sodium meals</p></li><li><p>A free cognitive test for the elderly based on peer-reviewed content, to detect cognitive decline</p></li></ul><figure data-type="image" data-version="v2" data-id="ymuTFnG48JPrTpeLoWSFN" data-size="best-fit" data-align="center"><img src="https://tribe-s3-production.imgix.net/ymuTFnG48JPrTpeLoWSFN?auto=compress,format" data-id="ymuTFnG48JPrTpeLoWSFN"></figure><figure data-type="image" data-version="v2" data-id="cX34F28zZdUygrW4x6aG1" data-size="best-fit" data-align="center"><img src="https://tribe-s3-production.imgix.net/cX34F28zZdUygrW4x6aG1?auto=compress,format" data-id="cX34F28zZdUygrW4x6aG1"></figure><p><strong>SDG 4: Ensure inclusive and equitable quality education and promote lifelong learning opportunities for all</strong></p><ul><li><p>An app for students with reading disorders, to hear their textbooks read out loud by taking a picture of the page and voicing it with AI</p><figure data-type="image" data-version="v2" data-id="MPvGXidr8vh1Sm4lNWRjQ" data-size="best-fit" data-align="center"><img src="https://tribe-s3-production.imgix.net/MPvGXidr8vh1Sm4lNWRjQ?auto=compress,format" data-id="MPvGXidr8vh1Sm4lNWRjQ"></figure></li></ul>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[An AI Chatbot That Knows What Your Course is About]]></title>
            <description><![CDATA[In theory, there’s a lot of good that an AI-savvy student can do. They can ask unlimited questions 24/7, they can dive deeper into and beyond the textbook while personalising their learning in a way ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/an-ai-chatbot-that-knows-what-your-course-is-about-HxNTaU6BMCgE0uy</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/an-ai-chatbot-that-knows-what-your-course-is-about-HxNTaU6BMCgE0uy</guid>
            <dc:creator><![CDATA[Joseph Lin]]></dc:creator>
            <pubDate>Wed, 11 Jun 2025 13:47:16 GMT</pubDate>
            <content:encoded><![CDATA[<p></p><figure data-type="image" data-version="v2" data-id="Y7YJzuiABaF864r7hehuH" data-size="best-fit" data-align="center"><img src="https://tribe-s3-production.imgix.net/Y7YJzuiABaF864r7hehuH?auto=compress,format" data-id="Y7YJzuiABaF864r7hehuH"></figure><p>In theory, there’s a lot of good that an AI-savvy student can do. They can ask unlimited questions 24/7, they can dive deeper into and beyond the textbook while personalising their learning in a way that only the very rich could afford until recently (through an army of tutors). Yet most students aren’t tech-savvy, so how can teachers encourage, monitor, and safeguard AI usage?</p><p>In September 2024, my colleagues and I started an experiment where we created a custom AI chatbot that is programmed with data specific to an Intro to Psychology course at a community college in Hong Kong. <strong>This chatbot had access to the course’s lectures, outlines, and other data, and it is explicitly instructed to act as a course tutor only and refuse to answer any unrelated queries.</strong></p><p>Students were introduced to the chatbot during course tutorials, which also came with very basic AI training such as showing them how to generate revision questions, to ask for analogies to aid understanding, to explain ideas in different languages, and of course telling them that AI answers can be wrong.</p><p>The start-of-semester survey gave us a few pleasant surprises: the majority of students know that AIs can give false answers, and many also note that cheating is a major risk (usually in the context of <em>other</em> <em>students</em> using it to cheat and creating unfair competition). However, they also reported that their AI use cases have been for replacing search engines (which is problematic because AIs can give factual mistakes), or using it to write/draft homework.</p><p>The chatbot’s usage rose gradually, with each midterm and deadline seeing a bump in usage. In the end-of-semester survey, AI usage frequency for the majority of students went from “twice a month” or “monthly or less” to “few times a week” and even “everyday”. We also received very different comments like “it’s easier to ask AI than to ask the teacher questions” or that “I can revise for a quiz faster with mock questions”. We believe that while rough around the edges, setting up AI course tutors represents one practical way to deploy AI while aligning with today’s curricula.</p><figure data-type="image" data-version="v2" data-id="nYNE7h-9JwC4YSKp1Y7Yo" data-size="best-fit" data-align="center"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7a9214bd-44c3-46b3-9ec5-75bf31f173ce_1822x2141.png" data-id="nYNE7h-9JwC4YSKp1Y7Yo"><figcaption class="!text-center !mx-auto !text-content-subdued !text-xs  !px-0.5 !my-1 !max-w-prose !mt-1 !rounded-none">An AI TA that never gets tired, and which happily answers questions at 3AM. (This no-code chatbot was created using Chatbase.co)</figcaption></figure><p>Several factors made this course well-suited to such a chatbot. It’s a large class, with nearly 300 students, which meant limited direct access to the lecturer, so there’s a lot to gain by introducing a 24/7 AI tutor. The course content is also introductory and well-established, such that even the base AI model (we used GPT-4o) could already give very good answers to the students’ questions, except the customisation ensures there is consistency and continuity in glossary, definitions, and assessment formats. Not to mention, it’s instructive to go through the chat transcripts to see whether students copied AI output verbatim, or to see how they are using AI to learn.</p><p>This project has been very encouraging and we are going deeper in the current semester, aiming to provide better training for students while scaling this tool to other courses by popular demand. I hope to give further positive updates as the semester progresses.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI Loves Creative Writing]]></title>
            <description><![CDATA[The fact that AIs can hallucinate and generate false content has been drummed into anyone who’s been paying attention since ChatGPT launched in 2023. It can be a serious issue in many use cases, but ...]]></description>
            <link>https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/ai-loves-creative-writing-skJ1dEYAQ7Bit0C</link>
            <guid isPermaLink="true">https://community.goodfuture.foundation/ask-your-teacher-04rdk79n/post/ai-loves-creative-writing-skJ1dEYAQ7Bit0C</guid>
            <dc:creator><![CDATA[Joseph Lin]]></dc:creator>
            <pubDate>Fri, 06 Jun 2025 10:49:03 GMT</pubDate>
            <content:encoded><![CDATA[<p>The fact that AIs can hallucinate and generate false content has been drummed into anyone who’s been paying attention since ChatGPT launched in 2023. It can be a serious issue in many use cases, but in creative writing lessons, a bit of randomness just makes for a more serendipitous story.</p><p>While AI labs are still trying to fix hallucinations by teaching models to reason (like OpenAI’s o1 family) and by grounding them in data (Anthropic’s Model Context Protocol comes to mind), here’s how a pilot lesson with Primary 5 to 6 students at the Hong Kong Academy for Gifted Education used AI to support ESL students: <br><br><strong>Lesson Plan</strong></p><ol><li><p><strong>Planning on Pen and Paper<br></strong>In this 12-hour course, students wrote a short story, converted it into a podcast drama script, recorded themselves performing the story, and generated images and audio accompaniment.</p><figure data-align="center" data-size="best-fit" data-id="gxKLX4duKAni0fjOOzGg4" data-version="v2" data-type="image"><img data-id="gxKLX4duKAni0fjOOzGg4" src="https://tribe-s3-production.imgix.net/gxKLX4duKAni0fjOOzGg4?auto=compress,format"></figure><p>To mitigate students outsourcing their thinking to AI, they began by creating character profiles and outlining the plot on pen and paper.</p></li><li><p><strong>Edit and Expand with AI<br></strong>Students typed their handwritten notes to form a prompt for the AI (we used GPT-4o). It was a deliberate choice to keep planning on pen and paper, because the data entry gives students an opportunity to edit and iterate their work as they type.</p><figure data-align="center" data-size="best-fit" data-id="wSl1WTX7IwdTeFeK36sfe" data-version="v2" data-type="image"><img data-id="wSl1WTX7IwdTeFeK36sfe" src="https://tribe-s3-production.imgix.net/wSl1WTX7IwdTeFeK36sfe?auto=compress,format"></figure><p>We also covered basic prompt engineering and AI literacy, emphasising cautionary tales like the New York lawyers whose AI-generated work had inaccuracies.</p><p></p><p>Students were taught to discuss and edit the story with the AI (e.g. “How can I make this part funnier?”) and given time to finalise a ~3-minute script fit for as many members as they have in their group (as a former language arts teacher, this is <em>such</em> a godsend).</p></li><li><p><strong>Generate Images and Soundtrack</strong></p><p>Each group reads their script aloud and each member gets to choose their favourite moment in the story. That is the moment they’ll use AI to generate, and students have to write image-generation prompts to get the look and style they want (Canva’s free K–12 plan works well, while paid options like Midjourney would give fancier results).</p><p></p><figure data-align="center" data-size="best-fit" data-id="89GYvD0qbskml56p92iej" data-version="v2" data-type="image"><img data-id="89GYvD0qbskml56p92iej" src="https://tribe-s3-production.imgix.net/89GYvD0qbskml56p92iej?auto=compress,format"></figure><p></p></li><li><p><strong>Record and Present</strong></p><p>While students can easily generate AI voices performing their script, that doesn’t help them practise speaking English. Therefore, students used an AI voice changer (we used Elevenlabs) to transform their own performance into different voices while preserving their intonation and cadence.</p><p></p><p>Example of student’s work:</p><p></p><figure data-align="center" data-size="best-fit" data-id="P95RB7QJljtEYxAuQWtSu" data-version="v2" data-type="image"><img data-id="P95RB7QJljtEYxAuQWtSu" src="https://tribe-s3-production.imgix.net/P95RB7QJljtEYxAuQWtSu?auto=compress,format"></figure><p>In the end, all the generated media were combined into a slideshow. Everyone listened to everyone else’s stories, everyone clapped, and the lesson was done!</p></li></ol>]]></content:encoded>
        </item>
    </channel>
</rss>