When Meta’s Ray-Ban smart glasses offered no developer access, we found another way. Through creative engineering, we’ve developed multiple AI-powered experiments that showcase the potential of smart glasses technology.
Experiment 1: “As We See” - AI Photography Mentor
The Challenge: Closed platform, no API access.
The Solution: WhatsApp video calls as a live AI bridge.
Our system streams real-time audio and video from the glasses through WhatsApp to custom software running OpenAI’s models. The AI analyzes what you see, responds with creative guidance, and routes audio back to the glasses — creating a seamless conversation with an AI photography mentor.
Key Features:
- Real-time scene analysis and creative suggestions
- Natural conversation about composition and lighting
- Voice-activated commands for image capture and direction
- Contextual guidance based on your surroundings
Experiment 2: Instant News Article Generation
The Concept: From glasses recording to published article in 5 minutes.
This experiment uses an automated WhatsApp bot pipeline: record an interview through the glasses, voice command “send to Car Wash,” and our AI processes the video for transcription, analysis, and professional article generation.
The Workflow:
- Record interview through Meta Ray-Ban glasses
- Voice command sends video to AI Car Wash via WhatsApp bot
- AI processes video for multi-modal analysis and transcription
- Article generated with headlines, thumbnails, and structured content
- Results delivered back via WhatsApp in minutes
Real-World Test: We recorded a 3-minute interview about the Johnny Ive and Sam Altman collaboration announcement. The AI generated a complete professional news article with headlines, structured content, and social media segments.
AI Car Wash - Complete Analysis Output
The final result: professional news article "Tech Icons Johnny Ive and Sam Altman Collaborate on Future Innovations" with transcript, headlines, thumbnails, and figure recognition — all generated from a 3-minute glasses recording.
Key Capabilities:
- Multi-modal analysis processing video, audio, and visual content
- Automated transcription with precise timestamps and quote extraction
- Professional formatting with headlines, thumbnails, and article structure
- Figure recognition identifying notable people and context
Both experiments showcase how creative engineering can unlock the potential of closed platforms, transforming smart glasses into powerful AI-driven tools for photography and journalism.