A device for talking to a character reincarnated as a plant. Sensors watch soil moisture, temperature, humidity and light, and pass the readings to the AI as feelings — thirst, cold — so it speaks up with a face and a voice. It starts talking when a motion sensor spots someone, so a child gets a cue to care, no numbers needed.
Judges found the experience appealing, with a motion sensor meaning the plant speaks to you first, and said that combined with a likeable character it has real power to catch a child's interest. They also credited the use of sensor data history.
The core is probably the translation of sensor readings into the language of a personality. A humidity percentage moves no child; being told it is thirsty gets the plant watered. Changing nothing but the representation of the same data changes behaviour, and that design decision is what separates this from a monitoring rig. Leaving the trigger to a motion sensor matters too, since it removes the need to go and operate something before anything happens.
See all winners of 第4回 Agentic AI Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).