Wake Word
A board trained on the class's own voice samples. Recordings never leave the room.
Skills · Edge AI
AI that stays in the room.
No cloud account. No student data leaving the school. Small models on a board students can hold. Classes 6 to 12.
- Classes
- 6–12
- Form of work
- Life forms or Materials & machines
- CBSE circular
- Skill-81/2025
- Runs on
- Small boards and sensors
The case
Why edge, plainly
- Budget. Small boards. A broken one is a lesson, not a crisis.
- Privacy. Recorded, trained, and deployed in the classroom. No accounts for minors.
- Pedagogy. Small memory teaches. The whole system stays visible.
The work
What students actually build
Our exemplars, not student work.
Bird Log
A feeder-side board that recognizes local bird calls. Offline, for days.
Plant Doctor, Offline
A camera that flags leaf disease. Lighting and angles humble every model.
Classes 6 to 12
Class by class.
Classes 3 to 5 are not here. Unplugged AI thinking belongs in our AI skill.
Classes 6 to 8
guided builds serving the three projects a year Circular Skill-81/2025 (28.10.2025) requires, under life forms and materials and machines.
Classes 9 to 10
students own the full loop. Complements AI (subject code 417) where offered.
Classes 11 to 12
memory budgets, power budgets, accuracy trade-offs, enclosure design.
Classes 6 to 12
A physics or computer-science teacher, or an ATL in-charge, can run this after training.
We cover electronics basics, the collect-train-deploy loop, and teaching a session where the model fails publicly. That is the curriculum. Models train locally, then run on the board alone. Same material as our Edge AI workshop, Arduino Day Agra 2026.
Equipment
Equipment is bought. Capability is built.
Small boards, plus sensors and cables. Many ATL kits already hold compatible microcontrollers: check first. CBSE's CSL equipment list is explicitly "suggestive", adoptable per readiness (Circular Skill-13/2026, 20.03.2026).
The skills map
Related skills.
Questions
Honest answers.
Does this need internet in the lab?
Very little, none during student sessions. Models train locally, then run on the board alone.
Isn't this too advanced for a school?
The engineering is real, the entry is gentle. A working Wake Word demo arrives fast.
We're considering AI too. Do we need both?
No. Choose Edge AI if privacy, connectivity, or budget is the constraint; AI for the 417 pathway.
Book a workshop
Half a day at your school. Here is what happens.
How a school and Hankernest find out whether Edge AI fits before anyone commits to a year. Inside your timetable, with your teachers and your students, on what you already own.
in the demo period
Your class builds
A wake-word demo: the class records its own voice samples, trains on the spot, and the board answers back before the period ends.
And learns. Why the model fails for some voices, and what that says about data.
- First period
A demo period with a class
One brief from this page, run as a lesson with one of your classes, on what the school already owns.
- Second period
Hands-on for your teachers
The same kit in their hands. Where it fails, what students ask, how the period is paced.
- Over tea
The timetable conversation
Where the periods come from, which classes, and which forms of work the projects would cover.
- Within the week
A written fit note
What we would run, what you already have, what you would buy directly, and a cost band. No obligation.
You pick the class and the period. We bring what the session needs.
Or just talk to us. info@hankernest.com, or +91-7000403607 on call and WhatsApp during office hours.