A team of Hyderabad researchers at the International Institute of Information Technology, Hyderabad, used artificial intelligence (AI) to study how 12 different biryani types are cooked. By analyzing video recordings, they discovered clear differences among biryani styles like Ambur, Bombay, Dindigul, Donne, Hyderabadi, Kashmiri, Kolkata, Awadhi, Malabar, Mughlai, Sindhi, and Thalassery. The study did not include the Moradabadi biryani. The researchers applied visual learning models to video data to spot unique cooking steps, ingredients, and techniques. They said, “By comparing the cooking process for different types of biryani, we can identify common patterns and variations in the cooking methods, ingredients, and techniques used.” Despite variety, common steps in biryani making were identified, such as soaking rice, marinating chicken, frying onions, and adding spices. These steps appear in many biryani recipes, even with regional variations. This research comes from a paper titled ‘How Does India Cook Biryani,’ authored by C.V. Rishi, Farzana S., Shubham Goel, Aditya Arun, and IIIT-H faculty member C.V. Jawahar. The paper was presented in December 2025 at the Indian Conference on Computer Vision, Graphics, and Image Processing in Mandi. The study could help with Geographical Indication (GI) tagging of biryani types, a challenge so far. For example, the GI tag effort for Hyderabadi Biryani was dropped after the local association refused to share cooking details, which are crucial for brand protection.