Session by session
- Session 31 · Ask & understandWeek 16
The cost of a false trigger versus a miss
Evidence: a question, sketch or new vocabulary
- Session 32 · Build & designWeek 16
Score held-out patterns at many thresholds
Evidence: a design draft, dataset or build
- Session 33 · ImplementWeek 17
Plot the trade-off and choose an operating point
Evidence: a working version, explained once
- Session 34 · Test & improveWeek 17
Confirm the choice on an untouched session
Evidence: a test log with at least one failure
- Session 35 · Explain & reflectWeek 18
Defend the budget to a non-specialist
Evidence: an individual explanation
- Local Python/scikit-learn
- P03 dataset plus a new held-out session
Precision, recall and false triggers per hour reported on an untouched session.
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
- RoboticsG12-P05
Trigger Timing and Latency Lab
A debounced trigger window and a measured end-to-end delay for the sound channel.
Sessions 21-25Builder and up - RoboticsG12-P06
Power-Budget Bench
A measured power budget for the model room, with a battery-life estimate checked against a timed run.
Sessions 26-30Builder and up - AIG12-P07
False-Trigger Budget Study
An operating threshold justified by the cost of false triggers against missed knocks.
Sessions 31-35Builder and up - IntegratedG12-P08
Confidence-Gated Smart Room
A smart-room link that acts only on confident, fresh predictions and logs every decision.
Sessions 36-40Builder and up
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.