Learning with LLMs

Learning with LLMs

IT Standard 14 8 hrs AI

This course covers how to use a large language model as a study and teaching tool with Google Gemini. It starts with the five elements of a good prompt, persona, objective, audience, context and boundaries, together with the Master Prompt strategy and the follow-up prompts that close a specific knowledge gap. It then covers the limitations of LLMs, including hallucination, training data cutoff and the memory ceiling, and the habit of verifying key claims against reliable sources. The second part moves from single prompts to reusable tools: a Gemini Gem holds a fixed system instruction written in Markdown so that a phase-based study activity behaves the same way every session, while the Canvas tool and Google Sheets with Apps Script turn a conversation into a working web app that can be deployed and shared. The course finishes with a full build cycle on a self-chosen HKDSE topic, in which participants ask Gemini for a plan-only proposal, cut the features that do not help, then generate, refine and submit the tool.

Course Enquiry

Learning objectives

  • Write structured prompts using persona, objective, audience, context and boundaries, and refine the output with follow-up prompts.
  • Identify where LLMs fail, including hallucination, knowledge cutoff and the memory ceiling, and verify key claims against reliable sources.
  • Build and share a learning tool as a Gemini Gem, a Canvas web app or a Google Sheets Apps Script web app.

Lesson plan

Introduction to prompt engineering | Describe the five elements of a good prompt: persona, objective, audience, context and boundaries | Explain the Master Prompt strategy, when to reset a conversation, and the limitations of LLMs including hallucination, training data cutoff and the memory ceiling | Hands-on: i) Write a master prompt in Gemini Thinking mode that generates 3-5 key points on a chosen topic for F5 students ii) Refine the answer with gap-analysis follow-up prompts that state what is understood and where the gap is iii) Rewrite the prompt in Markdown using Role, Objective and Requirements headings
Introduction to Gemini Gems | Compare a Gem with normal chat on consistency, setup and persistent knowledge | Structure a Gem instruction in Markdown with Role, Objective, Requirements and Input sections | Hands-on: i) Create a Gem that generates key points for a given subject and topic and test it in Fast mode ii) Build a phase-based study Gem that presents key points, tests with fact, understanding and application questions, diagnoses the knowledge gap and writes a four-panel comic transcript iii) Copy the generated image prompt into a new conversation and run it with the Create Image tool
Create learning tools with Gemini | Introduce the Gemini modes: Create Image, Canvas, Deep Research and Guided Learning | Compare a Canvas app with a Google Sheets Apps Script app, including static data snapshots and image support | Hands-on: i) Add the Canvas tool to an existing conversation, generate a working app from that conversation and share the link ii) Copy the sample Google Sheet and open Apps Script from the Extensions menu iii) Paste the provided Code.gs and Index.html, deploy as a web app with access set to Anyone, authorise access and open the deployed link
Build your own learning tool | Apply prompt engineering to plan, critique and build a tool for a self-chosen HKDSE topic that students find difficult | Hands-on: i) Ask Gemini for a plan-only proposal stating audience, context, objective and boundary ii) Filter the proposal against a relevance and clarity checklist, state why a feature is removed and ask for a simpler alternative iii) Generate and refine the code as a Canvas web app or a Google Sheets Apps Script app iv) Submit the screenshot and code, or the shareable link

Prerequisites

  • No coding experience is required
  • A Google account for signing in to Gemini and Google Drive

Software

  • Google Gemini (Fast / Thinking / Pro modes, Gems, Canvas, Create Image)
  • Google Sheets with Apps Script

Other requirements