Prompt to production: Building an AI app with Flutter
summary
Builds a cross-platform Flutter chat app that sends text, images and video to Gemini 1.5 Flash via Vertex AI in Firebase, configures a system prompt for diagnostic JSON responses, and decodes them into a scrollable list of diagnosis cards. Uses image_picker, video_player and Flutter Animate, keeps chat context in a Gemini chat session, and reports that sending a request is “one line to send a prompt” while the app runs on iOS, Android and web from a single codebase.
AI-written summary · about
chapters (10)
- 0:00The problem
- 1:01Diagnosing with Gemini
- 2:00Why build a custom app
- 3:02App overview
- 3:36Building the UI
- 5:11Integrating Vertex AI
- 7:37Managing app state
- 9:12Structured AI responses
- 10:55Adding media support
- 11:46Deployment and conclusion
related talks
36mEmpowering Your Flutter Apps with AI
01h 11mBuild Your Own AI Sidekick with Flutter
38mEnhance the customer experience
42mDart and Flutter and AI, Oh My!
42mMore Flutter and Dart and AI, Oh My!
47mAgentive Experiences With Flutter: What, How, and Why Bother?
22mFirebase Studio: AI-Powered Flutter Development
38mGenerative UIs: Using LLMs to Create Flutter Screens at Runtime