Make an AI Light Switch with micro:bit + CreateAI

1. Introduce the Activity
   • What if you could train a computer to turn lights on without touching a switch?
   • Where might that be useful?
   • How could a computer recognize your actions?
   • Today, you’re building a touchless, micro:bit and AI-powered light switch.
2. Introduce AI & Machine Learning
   • Machine learning means teaching a computer using examples instead of step-by-step instructions.
   • Explain simply:
     • You give examples (dataset)
     • The computer finds patterns in the data
     • It predicts what new inputs are
   • We’re going to teach it to recognize movements
3. Collect Training Data
   • Guide students in CreateAI
     • Create movement classes:
       • Clapping
       • Waving
       • Still
   • Connect your micro:bit to CreateAI
   • Record multiple samples for each class
   • The more good examples you give, the better your AI will work.
4. Train & Test the Model
   • Train model once you have recorded enough data, and see what your AI learned.
   • Students:
     • Click Train model
     • Test movements
   • Discuss:
     • Does it recognize movement correctly?
     • Where does it make mistakes?
5. Improve the Model (Iteration)
   • AI gets better with better data. Are there any classes that need more data to help improve the accuracy of detecting the movements correctly?
   • Students:
     • Add more sample data to the classes
     • Remove incorrect ones
     • Retrain and test
6.  Connect AI to micro:bit Code
   • Students:
     • Open project in MakeCode
     • Download to both micro:bits
   • Explain roles:
     • Sender micro:bit → detects movement
     • Receiver micro:bit → controls “light”
7. Program the Light Switch Logic in MakeCode
   • Walk students through creating the code or use the completed code link (provided within MakeCode) to share the completed code with students.
   • Discuss the behavior within the code:
     • Clap → send “lightsOn”
     • Wave → send “lightsOff”
     • Receiver:
       • “lightsOn” → LEDs ON
       • “lightsOff” → LEDs OFF
8. Test the System 
   •  Try your micro:bit AI light switch!”
   • Students:
     • Wear or hold sender micro:bit
     • Perform the three actions
   • Discuss:
     • Does the second micro:bit respond correctly?
9. Real-World Connection
   • Discuss:
     • What is this functionality similar to in the real world?
   • Options:
     • Smart home devices
     • Motion-controlled lighting
     • Touchless interfaces
     • Accessibility technolog

• Expect:
  • Model inaccuracies (valuable learning moment)
  • Need for multiple training attempts
• Emphasize:
  • AI is only as good as its data
  • Systems connect multiple devices
  • Students can design intelligent systems not just code

Reflection / Exit Ticket Ideas:

• How did your AI learn to recognize movements?
• What made your model more accurate?
• What happened when it made mistakes?
• How is this different from traditional coding?

Students can:

• Add a third action (dim lights)
• Control multiple micro:bits at once
• Add sound or external LEDs
• Build a smart room prototype
• Explore accessibility applications