S1-S3 Visual Arts: school garden design sprint (observe, propose, improve)

• StageS1-S3
• SubjectVisual Arts
• Learning strandreflection on the application of AI
• Official documentsAI Literacy Learning Framework for Primary and Secondary Schools · AI Literacy Learning Framework for Primary and Secondary Schools (Examples of Application Scenarios)
• Session timeOne 60-minute lesson: observe, propose, improve

Design sprint: pupils observe their campus, set criteria, use the school's approved AI tool to propose options, improve and critique one.

• AudienceTeachers Students
• ThemeHong Kong inquiry

• EquipmentAccess to one real outdoor spot on campus; printed worksheets; the school's approved AI tool
• Version1.8
• Last updated2026-10-17

What this solves

Pupils will soon ask an AI to “design a school garden for me” and hand in the pretty picture it makes as if it were their own design. Real design ability is not collecting images; it is observing a real place with your own eyes first, setting criteria, and then using judgement to check what the AI proposes.

This resource puts observation before asking the AI, across four segments: pupils go to one real outdoor spot on campus and record the things they can actually see — sun, ground surface, drainage, wind, who walks through, and what already grows there. Where they cannot tell, they write a question instead of inventing a number. They then turn those observations into four to six design criteria, ask the school’s approved AI tool for several layout options, and check each one against their criteria — anything they cannot justify is marked unsupported. Finally, they improve one option by hand and write a critique naming at least one thing the AI got wrong or could not know.

The core message: the AI’s images are not a plan, not evidence and not the finished work — the pupil’s own revised drawing and written justification are.

The resource can sit inside a school’s digital education planning and run in a visual arts lesson, assessed through the pupil’s own redrawing and written defence: pupils spell out their design criteria in a written prompt, then check the AI’s image recognition and generated options, and settle on their own redrawn version with copyright in mind.

Learning objectives

By the end, pupils can:

1. Describe one real outdoor spot on campus from their own observation (sun, ground, drainage, wind, foot traffic, existing plants), and write a question where they cannot tell rather than inventing a number.
2. Turn their observations into four to six checkable design criteria.
3. Write a design brief in their own words and use the school’s approved AI tool to ask for several layout options.
4. State, option by option, which of their own criteria each one meets, and mark anything they cannot justify as unsupported.
5. Improve one option by hand and write a critique naming at least one thing the AI got wrong or could not know.

Written for the junior-secondary learning stage, it covers the reflection on the application of AI strand of AI literacy, with human-AI collaboration and critical thinking at the centre.

How to use it

One 60-minute lesson, in four segments.

1. Introduction and outdoor observation (10 min) — Set the rule: “We record what we see; where we cannot tell, we write a question, not a number.” Make clear the finished work is the pupil’s own revised drawing and writing, not the AI’s image. The whole class goes to one real outdoor spot on campus and each pupil fills in the observation record: sun (at two named times of day), ground (paved, soil or planted), drainage, wind, who walks through, and what already grows there. Circulate and remind pupils to write “I cannot tell” as a question.
2. Set criteria and write the brief (15 min) — Pool the observations and agree four to six design criteria as a class, filling in the criteria worksheet (for example: shade at midday, low watering need, plants that survive a windy corridor, somewhere to sit, accessible to a wheelchair). Each pupil writes a design brief in their own words, from their observations and criteria, using the brief template.
3. Propose with AI and check option by option (15 min) — Give the brief to the school’s approved AI tool and ask for several layout concepts (not finished images). Remind pupils: the AI’s image is an option, not an answer. Fill in the concept-comparison table: which of my criteria does this option meet? What can I not account for? Mark anything I cannot justify as unsupported.
4. Improve by hand, critique and share (20 min) — Choose one option and revise it by hand on the revision page, annotating against the criteria and the site’s constraints. Write a short critique naming at least one thing the AI got wrong or could not know (for example it could not know the drainage you observed, the wind, or the walk-through route). Share the revised drawings and critiques, and restate: the AI’s image is not the finished work; the pupil’s own drawing and reasons are.

Answer key and marking notes

This design sprint is open-ended, but good answers share checkable features. The examples below are fictional; teachers can swap in their own campus spot.

A good observation record

Rule: pupils record only what they see; where they cannot tell, they write a question. If an official figure is needed (for example annual rainfall), the class should get it themselves from an official source such as the Hong Kong Observatory — this resource supplies no numbers.

A good criterion

A good criterion is checkable: it names a place and a situation, and can be checked with a yes or no. For example “between noon and one o’clock, the seating area must have shade” is better than “it should have shade”. If the class only writes criteria such as “looks nice” or “more flowers”, ask: “How would you check whether it has done that?”

A good concept comparison

What the teacher looks for: whether the pupil can say, for each option, which of their own criteria it meets; anything they cannot justify must be marked unsupported. Copying an AI image with no comparison table means the section is not done.

A good critique

A good critique names at least one thing the AI got wrong or could not know, and ties it back to the pupil’s own observation. For example (fictional): “The AI put the seating on the east side, but we observed that the east side is the windiest all day, so the option ignores the wind.” Writing only “it is badly designed” with no evidence is not a good critique.

Marking guide

The one rule that matters

The AI’s images are not a plan, not evidence and not the finished work. A pupil who hands in an AI image as their design has not done the task — the finished work is the pupil’s own revised drawing plus a written justification they can defend from their own observation. Teachers should restate this in every lesson.

Files

The full worksheet (observation record, criteria worksheet, design brief template, concept-comparison table, revision page and marking guide) is in the download file:

Worksheet (Word document, editable)

All places and examples in the worksheet are fictional and do not involve any real school, place or pupil.

Official documents

Every resource in this library is written to the AI Literacy Learning Framework for Primary and Secondary Schools and falls within the policy scope of the Blueprint for Digital Education Development in Primary and Secondary Schools.

This resource maps to:

• Supplement I: AI Literacy Learning Framework for Primary and Secondary Schools (p.1-8): pupils should understand AI’s abilities and limits, use it responsibly, and check its output critically rather than accepting it as given.
• AI Literacy Learning Framework for Primary and Secondary Schools (Examples of Application Scenarios) (p.16): a Visual Arts scenario for junior and senior secondary in which pupils design a bench for the school garden, interview the people who will use it, and use AI to see how a design sits in the real setting; this resource applies the same loop to a garden design sprint.

Learning strand: reflection on the application of AI

Official documents page: https://www.edb.gov.hk/en/edu-system/primary-secondary/applicable-to-primary-secondary/it-in-edu/debp.html

This page is an independent Beets teaching resource, not an official EDB document.

Feedback

If you have any comments or questions about this resource, or an idea for the next one, tell us on the feedback page.