Create a practical application that automatically catalogs your books by analyzing a video of your collection using Gemini Flash and Google AI Studio, then deploy it with Cloud Run to make it shareable.
with Claire Vo
Navigate to Google AI Studio and use a simple text prompt to define the functionality of your application. The model will interpret your request and generate the underlying structure of the app.
Create an app that takes a video of a person flipping through their book collection and extracts the author and title of every book shown.Use your phone to take a short video, slowly flipping through the books on your shelf or in a stack. The app will ingest this video, break it down into individual frames, and use Gemini Flash's vision model to analyze each frame.
The AI model will automatically identify the book covers in the video frames and perform Optical Character Recognition (OCR) to extract the text, specifically identifying and parsing out the author and title for each book.
Once the app is working as intended within Google AI Studio, use a service like Cloud Run to deploy it. This will make the app live and accessible via a simple, shareable web link.
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.