Session by session
- Session 51 · Ask & understandWeek 26
Labels and missing examples
Evidence: a question, sketch or new vocabulary
- Session 52 · Build & designWeek 26
Inspect a deliberately poor dataset
Evidence: a design draft, dataset or build
- Session 53 · ImplementWeek 27
Repair labels and balance the classes
Evidence: a working version, explained once
- Session 54 · Test & improveWeek 27
Retest using unchanged held-out examples
Evidence: a test log with at least one failure
- Session 55 · Explain & reflectWeek 28
Document what improved and what did not
Evidence: an individual explanation
- No-code model tool
- prepared object-image dataset
One fixed twelve-case test set used before and after repair.
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-P09
Reaction Timer
A simple device that records a response interval.
Sessions 41-45Innovation only - RoboticsG06-P10
Light-Value Reporter
A serial light logger with a simple observation table.
Sessions 46-50Innovation only - AIG06-P11
Dataset Repair Workshop
A dataset change log and an honest model comparison.
Sessions 51-55Innovation only - IntegratedG06-P12
AI Light-Cover Adviser
A supervised model-cover prototype combining learned advice and measured light.
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.