Pretty slick website. I also love how you using AI to generate all the food icons. It's so, so much nicer than just visually comparing text.
When I first found Cronometer and started using it daily, I did what every developer does and looked at what kind of data exists out there if I wanted to build my own app. The free data from the FDA was pretty bad/limited with massive holes and it would have taken a lot of effort to clean up.
Of course, Cronometer's best data comes from https://www.ncc.umn.edu/food-and-nutrient-database/.
Maybe you can sample your data and validate it against NCC's data via Cronometer to see if your LLM approach has legs when it comes to micronutrients and amino acids. And note that you have AIgen data that NCC's hand-measured database doesn't even have reliably, like choline, which seems like a red flag.
Thank you for the feedback.
Have you asked one of the LLMs used to tell you about the choline content of a food, even ungrounded? They are surprisingly good at reasoning about what kinds of foods tend to contain large amounts of choline because their training datasets will include all kinds of similar data points, even if the single food you're looking for doesn't have it listed explicitly.
The icons looks neat! What did you use to generate the icons so fast? I could use it in my plant app.