Edor.ai Learning Centre

AI literacy courses for Hong Kong teachers

Two free courses. The first explains in plain language how large language models actually work; the second teaches you to write prompts precise enough to use for planning, question setting, marking and classroom work. Written by people who taught, and every lesson says how the same technique is used inside this system — and what it still cannot do.

LLM Classroom: large language model foundations

28 lessons about 374 minutes

Starting from the Transformer architecture, tokenisation, parameters and self-attention, then on to the three training stages, RAG, quantisation, on-premises deployment, gating, and where this is heading. Explained with everyday analogies — no maths or coding background needed.

For: all teachers, panel heads, IT coordinators; no coding background needed

Module 1: What is actually happening inside a model
Module 2: How a model gets made
Module 3: The ecosystem and where models come from
Module 4: The concepts you genuinely need to build something
Module 5: On-premises deployment and frugal fine-tuning
Module 6: Safety, evaluation, and the limits you cannot design away
Module 7: Where this is heading

Syllabus

Prompt Engineering Classroom: what it looks like in a lesson

18 lessons about 241 minutes

Eighteen lessons, all set in Hong Kong classrooms: planning, tiered worksheets, question setting and rubrics, marking feedback, SEN adaptation, guided practice, administrative writing, grounded RAG answers, defending against prompt injection, and keeping a panel template library alive. Every lesson comes with prompts you can copy, in both languages.

For: classroom teachers, panel heads, teaching assistants; read LLM Classroom modules 1 and 4 first

Module 1: The fundamentals
Module 2: The situations you are actually in
Module 3: Paperwork, RAG and safety
Module 4: Going further, and keeping it working

Syllabus

Why these two courses were worth writing

Teachers do not need to become engineers, but they do need to know why AI gets things wrong, why it sometimes loses earlier context, and which data must never be pasted in regardless.
School-based AI work ends up in grant reports and professional development records, and that calls for material you can cite and explain.
The RAG, gating, quantisation and on-premises deployment running in this system are the same techniques taught here. Afterwards you will at least know what you bought.
Every lesson is free and public, so it can go straight into panel co-planning or a teacher workshop.

AI model database

Specs, pricing, release order and support status in this system for 15 model providers

Open the model database

Field Notes

Tools tested, models compared, and notes taken while running this in schools

Go to Field Notes

AI literacy courses for Hong Kong teachers

LLM Classroom: large language model foundations

Prompt Engineering Classroom: what it looks like in a lesson

Why these two courses were worth writing

Subscribe to Field Notes