Camera-Based Travel Assistant

I built an app with AI, and would like to share what I learnt from it, and hear feedback on my learnings.

The app: Web app whose homepage is device camera. Taking a picture prompts GPT to describe what’s in the image, and provide helpful advice when the image is of a landmark or food, which can be helpful when one is travelling. Images are saved in a history drawer that can be returned to. Opening on phone allows switching between back and front cameras.

The presentation: Technical demo demonstrating how I used Next’s Route Handlers and Vercel’s AI SDKs to stream responses from OpenAI’s Chat Completions API to client, and how I used Cursor to build the camera UI and write tests.