Quest 12 of 15
Prompting vs fine-tuning
Prompting changes the instructions and examples you give a ready-made AI model. Fine-tuning changes a model further using a carefully prepared set of examples, usually requiring technical expertise, data governance, and testing. Both approaches need clear goals, representative examples, and evaluation.
Start here
This module builds on earlier parts, but every important idea is explained in context. Prompting changes the instructions and examples you give a ready-made AI model. Fine-tuning changes a model further using a carefully prepared set of examples, usually requiring technical expertise, data governance, and testing. Both approaches need clear goals, representative examples, and evaluation. As you read, connect each concept to the worked example and ask what a person must still decide.
Big idea
Prompting changes the instructions and examples you give a ready-made AI model. Fine-tuning changes a model further using a carefully prepared set of examples, usually requiring technical expertise, data governance, and testing. Both approaches need clear goals, representative examples, and evaluation.
Learn one idea at a time
Read, explore, then mark each idea when you can explain it.
Idea 1 of 9
State the repeated task and describe a successful output. For library reminders, that could mean a respectful message containing the title, due date, return instructions, and no invented penalties.
Live interactive diagrams
Tap nodes, stages, or cards to explore — these diagrams match this module’s ideas.
Simple tool workflow idea
Your question or file (no private IDs).
Choose a deep dive
Open the topics you want to explore. The detail stays folded until you need it.
Deep dive 1Instructions versus adaptation
A prompt is an instruction given at use time; it is quick to revise and does not normally change the underlying model. Fine-tuning is a more involved adaptation that can make repeated responses more consistent for a narrow task.
Deep dive 2Data quality is a responsibility
Training examples can contain private information, errors, or unfair patterns. Organisations must have permission, documentation, security, and evaluation before using them for adaptation.
Deep dive 3Worked example: Prompting vs fine-tuning
A school wants consistent draft reminders for overdue library books. A responsible response is: First test a clear prompt and approved templates using fictional student data. Correct. A repeated low-risk task can begin with prompt testing and safe sample data. Use this case to separate what the technology contributes from what people contribute. The team should compare the intended outcome with a baseline where applicable, record important assumptions, and keep a clear route to correct or stop the process.
Deep dive 4Local check for Prompting vs fine-tuning
Ask whether the examples, data, and assumptions fit your school, company, or community. Generic demos often miss local names, laws, connectivity, and languages.
Deep dive 5Prompting vs heavier customisation
Most school tasks improve with better prompts and templates. Fine-tuning needs data governance — start small and approved.
One-minute challenge
Connect this lesson to real life
Name one situation where this idea could help, and one thing a person should still check.
Explore a real-world example
Use the arrows to connect the idea to a visible situation.
Photo example
Two levels of adaptation
Prompting guides one interaction; fine-tuning adapts a system for a repeated pattern. Both require testing and responsible data practices.
Key terms
Tap a term to flip and read the definition.
Optional further learningFree textbooks and trusted online resources
These sources informed the course structure. Use them to revisit a concept or study it in more depth.
Ready check
Tick each idea only when you could explain it without looking back.
Ready for practice? Take one repeated task and write what a good output must include and avoid.
Extra context (audience, logistics, curriculum notes)
Built for: High school pathway — Forms 1–6 friendly.
Formats: Learn scroll · Practice interactions · Quiz · Optional chat lab
Module 12 — Prompting vs fine-tuning
Next up
Ready for the next part?
When you've finished the reading, inline exercises, and knowledge check for this part, check the box to continue.