015 min
Walk a branch
Use a floor fork labelled rain/no rain and follow two weather cards.
Ask: “Does every card walk along both paths?”
Listen for: “No, the answer chooses a path.”
Brightlab
brightlab.Made for curious mindsbrightlab.Made for curious mindsBrightlab
Year 1 · Algorithms
Help Kiki choose inside or outside. Follow the weather arrows.
Go to the investigation ↓An annotated playground decision tree with three traces.
Help Kiki choose inside or outside. Follow the weather arrows.
A branch is a question with different paths. Our pretend planner checks rain and temperature before suggesting an indoor or outdoor activity. Following a rule correctly does not mean that the rule is sensible. People need to choose the conditions and test situations the first rule forgot.
Before this lesson: Follow a two-step instruction and answer a yes/no question. Useful earlier investigations: A rover with no common sense.
A branch is a question with different paths. Our pretend planner checks rain and temperature before suggesting an indoor or outdoor activity. Following a rule correctly does not mean that the rule is sensible. People need to choose the conditions and test situations the first rule forgot.
Follow a two-step instruction and answer a yes/no question. Useful earlier investigations: A rover with no common sense.
Draw a forked path on paper. Prepare fictional weather values: rain at 20°C, dry at 22°C, dry at 39°C. Explain that this classroom model is not an official heat or school-play policy.
ACARA V9 AI curriculum connection ↗ · Technologies ↗
A complete teaching sequence · 40 minutes
Use a floor fork labelled rain/no rain and follow two weather cards.
Ask: “Does every card walk along both paths?”
Listen for: “No, the answer chooses a path.”
Record what a rain-only planner will do at 39°C with no rain.
Ask: “What does this rule check, and what does it ignore?”
Listen for: “It checks rain and ignores heat.”
Change the temperature one step at a time and watch the highlighted decision path. Keep rain fixed. Then hold temperature fixed and test rain.
Ask: “Which question changed the suggestion?”
Listen for: “The temperature question crossed its number.”
Remove the heat check and test the dry hot card. Discuss why mechanically correct execution can be unsuitable.
Ask: “Did the computer make a mistake following the rule?”
Listen for: “No; our rule forgot the hot day.”
Choose an illustrative heat threshold and test rain, mild dry and hot dry cards. Draw the improved tree.
Ask: “Does your repair still allow the mild dry day?”
Listen for: “Yes, it goes along the cooler branch.”
Each pair names the human who should decide actual playground practice.
Ask: “Who is responsible for a real decision?”
Listen for: “The teacher or school, not this pretend planner.”
A rule works in every situation.
Dry weather can still be too hot for an activity; correct execution exposes an incomplete rule.
Add a heat branch and show three traces that protect the hot case while preserving the mild case.
Give a previously unseen temperature and ask for the complete branch trace. If the learner guesses from common sense, ask them to follow the displayed questions literally.
| Criterion | Beginning | Secure | Extending |
|---|---|---|---|
| Tracing | Guesses an outcome | Follows the displayed branch | Explains the exact threshold case |
| Rule repair | Adds an unrelated condition | Repairs the hot-day failure | Tests the repair against all three weather cases |
Use sun/rain pictures alongside words and only cooler/hotter values. Accept pointing along the path.
Add equipment availability on paper. Find a case requiring a third outcome rather than only indoors/outdoors.
All temperatures are fictional teaching inputs. Actual weather decisions follow school policy and adult judgement.
Shared device? Turn remembering off. A project file lets you continue on another device.
Your browser is the laboratory
Help Kiki choose inside or outside. Follow the weather arrows.
The initial planner asks only whether it is raining. Rain means indoors; dry means outdoors. A heat branch can be added at an illustrative threshold of 32°C. Test dry weather at 39°C.
The experiment opens after your prediction.
There is no penalty for being surprised.
Apple Silicon · PyTorch MPS
Test 4,096 synthetic temperatures in both rain states, exposing hot dry cases missed by a rain-only rule. Change the heat branch and compare exact counts.
Teacher-operated extension: students predict and interpret the visual report together.
The bundle contains lesson-specific working code, a configuration file, a reactive notebook, a deterministic CPU check and hardware setup instructions. Acceleration is reported only after a tensor operation and result read-back succeed.
Download Mac Studio investigation ↓unzip y1-branch-mac-pathway.zip -d y1-branch-mac cd y1-branch-mac bash setup-mac.sh source .venv/bin/activate python experiment.py --device mps --output results marimo edit notebook.py
CPU and available-device execution status is recorded in the downloaded README and validation report. DGX Spark execution requires that hardware; static validation alone does not establish GPU compatibility or performance. The browser lesson remains fully available without this extension.
NVIDIA DGX Spark · PyTorch CUDA
Test 4,096 synthetic temperatures in both rain states, exposing hot dry cases missed by a rain-only rule. Change the heat branch and compare exact counts.
Teacher-operated extension: students predict and interpret the visual report together.
The bundle contains lesson-specific working code, a configuration file, a reactive notebook, a deterministic CPU check and hardware setup instructions. Acceleration is reported only after a tensor operation and result read-back succeed.
Download DGX Spark investigation ↓unzip y1-branch-dgx-pathway.zip -d y1-branch-dgx cd y1-branch-dgx bash run-dgx.sh # Open the localhost notebook URL printed by the container.
CPU and available-device execution status is recorded in the downloaded README and validation report. DGX Spark execution requires that hardware; static validation alone does not establish GPU compatibility or performance. The browser lesson remains fully available without this extension.
An annotated playground decision tree with three traces.
Download the editable handout →