Session by session
- Session 11 · Ask & understandWeek 6
Image examples versus water sensing
Evidence: a question, sketch or new vocabulary
- Session 12 · Build & designWeek 6
Label dry/wet fabric photos
Evidence: a design draft, dataset or build
- Session 13 · ImplementWeek 7
Train and keep test images separate
Evidence: a working version, explained once
- Session 14 · Test & improveWeek 7
Compare mistakes under different backgrounds
Evidence: a test log with at least one failure
- Session 15 · Explain & reflectWeek 8
Produce a small model card
Evidence: an individual explanation
- Computer
- no-code model tool
- prepared fabric images
Twelve held-out images; report results rather than claim reliable rain prediction.
A model, an evaluation study or an AI-checking workflow.
Completion needs the artefact, an honest test log, an individual explanation and no open safety or privacy issue.
Projects in the same block
- RoboticsG06-P01
Programmable Signal
A programmed signal with an annotated sketch and code.
Sessions 01-05All plans - RoboticsG06-P02
Light-Driven Servo
A light-responsive servo model with two bounded positions.
Sessions 06-10All plans - AIG06-P03
Wet-or-Dry Image Lab
An image classifier tested on non-personal fabric images.
Sessions 11-15All plans - IntegratedG06-P04
Laundry Decision Desk
A human-reviewed laundry-cover model showing two kinds of evidence.
Sessions 16-20All plans
For school leadersChoose a starting point.
Build from evidence.
Pick the classes and a plan. We map the timetable, kit and safety checks with you, then pilot one class first.
- Prospectus and class-wise plan
- Kit and readiness check
- Pilot one class first
- Evidence at every milestone
Let's plan your pilot.
Share a few details and we will send the right plan for your classes.