Session by session
- Session 16 · Ask & understandWeek 8
Define a model-based shade recommendation
Evidence: a question, sketch or new vocabulary
- Session 17 · Build & designWeek 9
Connect logged sensor data to a prediction
Evidence: a design draft, dataset or build
- Session 18 · ImplementWeek 9
Map advice to a manual-approved servo position
Evidence: a working version, explained once
- Session 19 · Test & improveWeek 10
Test missing data and disagreement
Evidence: a test log with at least one failure
- Session 20 · Explain & reflectWeek 10
Explain how measured light differs from a forecast
Evidence: an individual explanation
- P01/P02 rigs
- local model
- reviewed serial or manual link
Twelve readings including three invalid/unknown inputs.
A laptop model sends named commands only after bench tests, with a simulator as fallback.
Completion needs the artefact, an honest test log, an individual explanation and no open safety or privacy issue.
Projects in the same block
- RoboticsG09-P01
Analog Measurement Lab
A light-measurement rig and a labelled dataset.
Sessions 01-05All plans - RoboticsG09-P02
Servo Position Bench
A one-servo positioning rig with calibrated limits.
Sessions 06-10All plans - AIG09-P03
Python Light Classifier
A simple light-state model compared with a transparent rule.
Sessions 11-15All plans - IntegratedG09-P04
AI Shade Adviser
A supervised shade-control model using a laptop prediction.
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.