Session by session
- Session 51 · Ask & understandWeek 26
Intent labels and non-personal text
Evidence: a question, sketch or new vocabulary
- Session 52 · Build & designWeek 26
Train on a small classroom command set
Evidence: a design draft, dataset or build
- Session 53 · ImplementWeek 27
Test paraphrases and unknowns
Evidence: a working version, explained once
- Session 54 · Test & improveWeek 27
Map labels to permitted named actions only
Evidence: a test log with at least one failure
- Session 55 · Explain & reflectWeek 28
Document when to ask a person
Evidence: an individual explanation
- Local Python
- synthetic command examples
Twenty held-out phrases with at least five unknowns.
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
- RoboticsG10-P09
Gesture Input Mapper
A one-joint flex-input controller, not an ML gesture recogniser.
Sessions 41-45Innovation only - RoboticsG10-P10
Sensor-Interlocked Arm
An arm model whose movement is inhibited by a separate sensor rule.
Sessions 46-50Innovation only - AIG10-P11
NLP Command Classifier
A restricted text-intent model with explicit refusal behaviour.
Sessions 51-55Innovation only - IntegratedG10-P12
AI Command Approval Console
A supervised command console; text never becomes arbitrary code or angles.
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.