
Dr. James Bedford - University 3.0: A Pedagogy-First Approach to Vibe Coding
Cohere16 June 2026Watch on YouTube
What you'll learn
- Teachers without technical background can create their own custom educational software using AI and LLMs, without needing programming skills
- Vibe coding embraces 'Entangled Pedagogy': technology, pedagogy and local classroom context are inseparable and cannot be addressed with generic solutions
- Hyper-local, pedagogically designed software outperforms generic platforms because it precisely meets the specific needs of your own students
- The Ninety-Five Percent Rule: focus on building the core 95% of your app, and use AI to complete that final 5% rather than striving for perfect code
Frequently asked questions
What is 'vibe coding' and how does it help teachers?
Why is generic EdTech software not effective according to Dr. Bedford?
What is the 'Ninety-Five Percent Rule' in vibe coding?
How does vibe coding fit into the concept of 'University 3.0'?
Topics
Read next
Description from the channel
00:00 Welcome and Speaker Intro 01:32 Why Vibe Coding Matters 04:13 Air Con Beats Laptops 05:19 EdTech Backlash and Opportunity 08:56 Self Regulated Learning Lens 11:34 Cognitive Load and Offloading 17:13 Vibe Coding for Better Learning 19:44 University 3.0 and Co Creation 21:57 Entanglement Pedagogy Explained 24:25 Three Ps Framework 29:08 The Ninety Five Percent Rule 29:49 Finish the Last Five Percent 30:53 Planning and Governance Questions 33:04 Co-Designing With Students 35:09 Math Assistant Live Demo 39:54 Complexity and Time to Build 42:03 Beneficial Offloading Signals 44:25 Beyond Chatbots to Voice and Video 47:28 Managing Codebase and Refactors 50:40 More Vibe Coding Use Cases 53:39 Closing and Connecting There has ironically never been a worse time for EdTech to be this easy to build. While recent studies suggest that simply installing air conditioning has a greater impact on student outcomes than giving every child a laptop, the EdTech industry has come under fire as it continues to push generic, profit-driven, “one-size-fits-all” software that may be benefiting no one. But what happens when the barrier between natural language and functional code completely dissolves? What happens when teachers can make their own software to meet the needs of their students? Enter "Vibe coding”. In this session, Dr. James Bedford explores the dawn of University 3.0—a paradigm shift moving away from "Consumer AI" and toward the "Teacher-as-Creator." With the rise of advanced LLMs, educators with zero technical background can quickly develop their skills to start engineering their own hyper-local, pedagogically aligned technological solutions. Drawing on real-world examples—like building a multilingual Socratic math bot complete with digital canvas integration—this talk will explore how we may be able to finally reject generic platforms in favour of an 'Entangled Pedagogy (Fawns 2022) empowering us to create tech solutions that meet the specific, localised needs of our students. Join us as we discuss the superpowers (and the pitfalls) of vibe coding, how to navigate institutional red tape, and why the future of impactful, inclusive EdTech might be built by the teachers themselves. What You Will Learn: • The Shift to University 3.0: How the dissolution of the coding barrier is empowering educators to become software creators rather than software consumers. • Entangled Pedagogy in Action: Why technology, pedagogy, and local classroom context cannot be separated, and how vibe coding solves the "generic software" problem. • Surviving the "Vibe Trap": Practical insights on the novelty effect, technical debt, and why building apps with AI requires more than just "prompt and pray." • Real-World Application: A look at custom, privacy-centric AI tools currently being built and deployed in Higher Education using natural language. James Bedford is an award-winning writer and educator with over 12 years’ experience working in higher education. He holds a PhD in Creative Writing from UNSW and is a Senior Fellow of the Higher Education Academy. He currently serves as an Education Specialist in Artificial Intelligence at UNSW College. This session is brought to you by the Cohere Labs Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. We'd like to extend a special thank you to Rafay Mustafa Leads of our EdTech group for their dedication in organizing this event. If you’re interested in sharing your work, we welcome you to join us! Simply fill out the form at https://forms.gle/ALND9i6KouEEpCnz6 to express your interest in becoming a speaker. Join the Cohere Labs Open Science Community to see a full list of upcoming events (https://tinyurl.com/CohereLabsCommunityApp).