Inspiration

We’ve all been there—watching a mouth-watering Eitan Bernath video and wanting to cook it, only to get stuck pausing the video dozens of times to write down ingredients. Qook was inspired by the need to bridge the gap between "that looks good" and "I'm cooking this right now."

What it does

Qook transforms a YouTube URL into a complete cooking guide in seconds. It provides an AI-powered recipe summary, extracts a precise list of ingredients, and organizes them into a smart shopping cart. Most importantly, you can easily share your shopping list with family or friends, making grocery runs more collaborative.

How we built it

We built Qook by integrating the YouTube Transcript API to retrieve raw video data and Google’s Gemini model to process that information into structured, easy-to-read recipes. For monetization, we used RevenueCat to manage premium subscriptions seamlessly, allowing us to focus on the core AI-driven user experience.

Challenges we ran into

Our biggest challenge was optimizing the response latency and output accuracy of Gemini. We spent a significant amount of time on prompt engineering and fine-tuning to ensure the AI provided lightning-fast responses while maintaining high precision in ingredient measurements and cooking steps.

Accomplishments that we're proud of

We are incredibly proud of creating a seamless "one-click" flow from a simple video link to a functional, shareable shopping list. Additionally, implementing a robust, production-ready paywall using RevenueCat in record time was a huge win for our development speed.

What we learned

We learned that user friction—especially waiting for AI responses—is the ultimate enemy of inspiration. By leveraging tools like RevenueCat and optimizing our LLM pipeline, we realized how much more value we can provide when we minimize technical delays for the user.

What's next for Qook

We plan to expand support to Instagram Reels and TikTok, integrate with local grocery delivery APIs for instant purchasing, and introduce AI-driven meal planning based on users' saved recipes.

Built With

Share this project:

Updates

Submission history