Session by session
- Session 56 · Ask & understandWeek 28
Convert model output into a short label
Evidence: a question, sketch or new vocabulary
- Session 57 · Build & designWeek 29
Add clear unknown and error messages
Evidence: a design draft, dataset or build
- Session 58 · ImplementWeek 29
Connect the label to a manually updated LCD demo
Evidence: a working version, explained once
- Session 59 · Test & improveWeek 30
Test unreadable/uncertain inputs
Evidence: a test log with at least one failure
- Session 60 · Explain & reflectWeek 30
Explain data movement and permissions
Evidence: an individual explanation
- P03 classifier
- LCD rig
- teacher serial demonstration optional
Ten cases; unknown remains distinct from a negative class.
The AI suggests. A person checks and operates the hardware.
Completion needs the artefact, an honest test log, an individual explanation and no open safety or privacy issue.
Projects in the same block
- RoboticsG07-P09
Parking Assistant
A model parking aid with defined alert bands.
Sessions 41-45Innovation only - RoboticsG07-P10
Event Counter
A tabletop object counter with recorded limitations.
Sessions 46-50Innovation only - AIG07-P11
Reusable Evidence Checker
A structured AI-output review workflow with evidence references.
Sessions 51-55Innovation only - IntegratedG07-P12
AI Status Interpreter
An AI-assisted status display with an operator-controlled hardware link.
Sessions 56-60Innovation only
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.