• Example of Using a Local LLM in Schools: Empowering New Teaching Assistants with Instant Pupil Data Insights

    Onboarding a new Teaching Assistant (TA) often involves a time-consuming handover of crucial pupil data, which is often scattered across various paper and digital files. This prototype demonstrates how a local Large Language Model (LLM) can instantly summarise a pupil’s background, including behaviour and exclusion reports, by processing secure, internal documents. Crucially, every piece of…


  • How a Local LLM Can Transform SEMH Support for Pupils in UK Schools

    Educators struggle to provide effective, immediate support for pupils with SEMH needs because critical data is often scattered, buried, or forgotten. We propose using a private, secure Local Large Language Model (LMM) that is trained exclusively on the pupil’s individual data, reports, and specialist advice. This innovative system acts as an ‘organisational memory,’ preventing valuable…


  • From Paperwork to Partnership: The Power of NotebookLM for SENCos and Teachers to support pupils with additional needs

    After watching this video yesterday, I’ve been having a bit of a tinker with Google’s NotebookLM recently, and a genuinely exciting possibility for its use in schools has sprung to mind. As many of you know, I’ve previously explored how we can responsibly harness AI to support our pupils. If you missed them, I’ve written about using ‘Gems’…


  • How to use Google Gems in Education: A Step-by-Step Guide

    Following on from my previous post about building a local Large Language Model (LLM) to help assess and document pupil Social, Emotional, and Mental Health (SEMH) needs—which you can read all about here—I’ve had a rather fascinating afternoon yesterday playing around with Google Gemini. I’ve been creating a few custom AI agents, or ‘Gems,’ and I…


  • Why Ray Dalio’s AI Clone validates my approach to SEMH support (and highlights a public sector problem)

    For the last few moths I have been exploring building a local LLM specifically trained on data from pupils with additional SEMH needs and also SEMH frameworks and approaches. Yesterday I read an article from Ray Dalio discussing building an AI Clone of himself that is trained on his 40 years experience in finance. I…


  • AI, Therapy & Schools: What OpenAI’s Therapist Network Can Teach Us About Local LLMs for SEMH Support

    Recently Forbes published an article by Lance Eliot announcing that OpenAI plans to augment ChatGPT with an online network of human therapists. The concept is that, when ChatGPT detects signs of distress, it would hand off to a vetted therapist within its platform. This merges AI’s pattern‑recognition abilities with human professional judgment, creating a hybrid…


  • Using AI to create a custom reading book for a pupil that is 7 years old but has a reading age of a 4/5 year old

    I am excited by this! I just quickly used Google Gemini to create the attached, using the below prompt. I think this is a game changer in using AI in schools and can help any child, of any age, with any interested irrelevant of their reading age. Here is the prompt so you can have…


  • AI & Robots are awesome…but so are cardboard boxes!

    By blending innovative technology with hands-on projects, we can provide a well-rounded educational experience that caters to the diverse needs of our learners. Ultimately, it’s about striking a balance between the digital and the physical, ensuring that every child has the opportunity to thrive.


  • Bridging Policy and Practice: A Local LLM for SEMH in Schools 

    In the Department for Education’s Areas of Research Interest report, AI is presented not as a silver bullet but as a tool with powerful promise — one that must be deployed with care, equity, and rigorous evaluation. My project to build a local LLM at my SEMH provision is very much in step with that…


  • Building a Local LLM for Schools: A Privacy-Focused Guide to assess and document pupils’ SEMH needs and progress 

    At the SEMH provision I run, I been working on creating practical tools to help staff capture daily observations of children’s social, emotional, and mental health (SEMH) progress in a structured way. The aim is to ensure that day-to-day insights can feed into AI systems to generate weekly reports, 24-week (end of placement) progress reviews…