← Back to the work

GLASSBRIDGE / ANDROID · RAY-BAN META COMPANION

Glassbridge

I wanted to ask questions through my smart glasses and hear an AI reply. This Android prototype brings the settings and conversation controls together. Testing with the physical glasses and a live AI service is still next.

Glassbridge / A closer look01 / 06
Session controls and image questions. Portfolio copy study.

The idea was to ask questions about a photo through my glasses.

I wanted to ask a question about what the glasses were looking at and hear a reply. For that to work reliably, the app would need a new photo for each question and an obvious way to stop recording or clear the conversation.

The Android prototype brings the controls together.

The Android prototype brings voice input, a fresh photo, a spoken reply and conversation controls into one screen. It includes settings for OpenAI, Gemini and compatible services. I have checked the build and emulator interface; the physical glasses and live-provider trial still need testing.

I made each question start with a fresh photo.

I designed the flow around one question and one fresh photo, followed by a spoken reply. Cancel and clear controls stay close by.

A failed capture must not send an old photo.

If capture fails, the flow must not quietly reuse an old preview. That would give the assistant the wrong scene while making the interaction appear successful.

Recording starts when I ask and stops when I cancel.

Push-to-talk starts the interaction. Cancel and leaving the foreground stop media work. These controls matter because a camera on glasses is different from an ordinary text box.

Changing the AI service clears the previous access key.

Changing a custom endpoint clears the existing API key. Sending is explicit and billable requests are not automatically retried.

IN PRACTICE

Where you can use it and how I built it.

Where it can help

  • Ask a directed question about a freshly captured scene.
  • Choose a supported provider or a compatible custom endpoint.
  • Use phone dictation or a selected photo when the intended capture path is unavailable.

Built with

  • Kotlin
  • Jetpack Compose
  • Meta Wearables SDK
  • Android TTS
Kotlin / Compose
Native Android interface and session controls.
Meta Wearables DAT
Official glasses integration path.
Android audio / TTS
Voice input, dictation fallback and spoken replies.
Keystore / AES-GCM
Encrypted provider settings on the phone.
HTTPS providers
OpenAI, Gemini and compatible custom endpoints.
Glassbridge setup screenshot with portfolio copy Choose your assistant and an empty API key field.
Choosing an assistant. Portfolio copy study. Select to see the full image.
Glassbridge conversation screenshot with shorter portfolio copy and no questions yet.
A new conversation. Portfolio copy study. Select to see the full image.
Glassbridge session screen.
Glassbridge session view. Select to see the full image.
Actual Glassbridge setup screen with AI-provider choices and an empty API key field.
Provider choices and connection settings. Select to see the full image.
Actual Glassbridge conversation screen with no conversation or provider response.
The conversation screen before the first question. Select to see the full image.