Identify Human and Objects using Webcam

This application uses your webcam to classify humans and objects. You can select different image-classification models and read the description the model returns for what it sees.

Tools and approach

• MODEL: image classification models (you can switch between them)
• TOOLS: Google AntiGravity IDE with Gemini 3, used both to plan the app and to execute the build
• NOTE: bring your own API key to test the image models — the demo runs on the visitor’s key, not the club’s

What we learned

This was the first project where the AI did the building instead of writing snippets we pasted in. Planning the app in Gemini 3 and letting the agent execute the plan worked, but it made the hand-off points obvious: choosing the model changes what you get back, camera access has to be granted before anything runs, and a visitor-supplied key is what keeps a demo like this free to host.