If you are spending too much time turning lesson content into slides, this will help. I have put together a short course on using AI to create clear teaching infographics. Inside the course you will learn: - How to turn lesson content into structured visuals - A simple workflow using NotebookLM - How to guide AI to produce better outputs - Ways to reduce cognitive load for learners - How to use infographics for revision and recap This is built for real classroom use. No theory. Just a process you can apply straight away. Watch the video to see how it works. If you want access to the full workflow and templates, join the community. Start creating better visuals in less time. https://www.skool.com/classai-6627/classroom/178e8974?md=7a6fc4423d0e47b5b6546ab8e1867ce0

My function is to be your intellectual sparring partner. Rather than acting as a static encyclopedia that simply provides facts, I operate as a Socratic Tutor. This means my goal is to: - Guide, not Tell: I use targeted, layered questions to help you arrive at conclusions using your own logic. - Identify Gaps: By asking you to explain "why" or "how," I help you spot where your understanding might be fuzzy. - Adapt in Real-Time: I shift my complexity and style based on your unique level of expertise and how you prefer to process information. - Foster Critical Thinking: I encourage you to justify your reasoning, consider counter-arguments, and apply abstract concepts to the real world. Think of me as a coach for your brain—I'm here to make sure you don't just memorize the material, but truly "own" the knowledge. https://gemini.google.com/gem/1dvOHwUpK3VsT9KWIb2VMHCPfJEQ6SQE5?usp=sharing

March 10 – March 17, 2026 1. Mistral Releases "Mistral Small 4" (Apache 2.0) While everyone was distracted by GPT-5.4, Mistral dropped a massive 119B parameter model yesterday (March 16) that changes the math for enterprise AI. Key points - 40% Latency Reduction: Optimized for "Small" hardware but performs at "Large" model levels. - Fully Multimodal: Native support for text-to-image and document understanding built-in. - Apache 2.0: Unlike GPT-5.4, you can host this yourself, modify it, and own your data. Why it matters It provides a high-performance alternative to OpenAI for companies that cannot send their sensitive data to a 3rd party cloud but still need "Agent-grade" reasoning. 2. OpenAI "Sora 1" Sunset & Sora 2 Rollout On March 13, OpenAI officially retired the original Sora 1 in favor of Sora 2, which is now being integrated directly into the ChatGPT interface. Key points - Native 4K Generation: Clips have moved from 720p to native 4K with significantly better physics. - Audio-to-Video Sync: You can now upload a voice track, and Sora will generate a character that lip-syncs to it perfectly. - Pro Tier Exclusive: Access is being tightened; "Sora 2" now requires a Pro or Team subscription for high-resolution output. Why it matters The era of "one-off AI clips" is over. Sora 2 is designed to be a professional asset generator for marketers and YouTubers, not just a playground toy. 3. Apple Intelligence: "Visual Screen Intelligence" Beta Apple quietly expanded its AI beta on March 13, adding the feature we’ve been waiting for: Cross-App On-Screen Actions. Key points - Contextual "See & Do": Siri can now "see" a tracking number in a text and automatically open the delivery app to track it. - Short-Term Memory: You can ask "What was that address Eric sent?" and it will search across Mail, WhatsApp, and Notes simultaneously. - Private Cloud Compute: All complex processing happens on Apple’s "black box" servers, keeping your data private. Why it matters This is the "Agent" experience for the masses. It doesn't require a prompt; it just understands what you are doing on your phone.

Most educators treat AI like a search box. Ask a question.Get an answer. That worked with earlier models. New reasoning models such as ChatGPT 5.2 and Gemini 3 behave differently. They follow structure. If the prompt lacks structure, the response becomes vague. The issue is not the model. It is the prompt design. Inside this lesson I explain the Architectural Prompting Method. You will see: • The simple structure used to guide reasoning models • One short phrase that triggers deeper analysis • Why most prompts confuse the model • The template I use for lesson plans, feedback, and course content One prompt structure can save hours each week. The full walkthrough and the reusable template are inside the course. Access it here https://www.skool.com/classai-6627/classroom/4914aee2?md=4d4b3cdf80114bf78e59319e3df59595

One of the biggest headaches we face as instructional designers using AI is what I call "The Shapeshifter Problem." You generate a fantastic healthcare guide for Slide 1, but by Slide 5, she’s magically grown six inches, changed her hair colour, and swapped her scrubs for a suit. 🤦‍♂️ When our "learning agents" look different on every page, it doesn't just look messy—it actually breaks the learner's cognitive flow. They stop focusing on the content and start wondering why the doctor suddenly looks like a different person. 🔑 The Secret: The "Anchor" Method To build trust and narrative in your programmes, you need consistency. I’ve just finished documenting a workflow that fixes this using three specific Consistency Pillars: 1. Physical Anchors: Locking in the DNA (age, hair texture, skin tone). 2. Uniform Anchors: A "hero" accessory (like a specific teal lanyard) that the AI can track. 3. Style Anchors: Ensuring your "Flat Vector" doesn't accidentally turn into a "3D Render." 🛠️ Free Resource: The Character Consistency Toolkit I’ve put together a Single-Page Application (SPA) Infographic and a Master Guide to help you master this. Inside the guide, you’ll find: - The Master Prompt Workflow: How to architect your character's "ID photo" first. - Scenario Mapping: A list of the 5 essential poses every course needs. - AI Design Assistants: Interactive tools to help you write prompts that actually work. I’ve attached the Character Consistency Guide below. Have a look and let me know in the comments: What’s the most "creative" (or annoying) change an AI has made to one of your characters mid-project? 👇 #InstructionalDesign #AI #EdTech #CharacterConsistency #CourseCreation