Good question — this was one of the trickiest parts to get right.
When you say "had a burger," the AI makes an educated guess based on a typical burger and shows its assumption: "Burger (~200g patty, standard bun) — ~550 kcal"
If you say "had a big burger," it'll bump the estimate: "Large burger (~250g patty) — ~700 kcal"
The key is it always shows what it assumed — portion size, ingredients, etc. So you instantly see if it's off.
If it guessed wrong, you just correct it in the chat: "it was a smaller patty, maybe 150g" or "add cheese and bacon" — and it recalculates.
The goal was making corrections conversational instead of form-based. Feels faster than hunting through dropdowns.
Not perfect, but gets you in the right ballpark quickly. And if you want precision, you can always go detailed upfront: "200g beef patty, brioche bun, slice of cheddar, lettuce, tomato."
When you say "had a burger," the AI makes an educated guess based on a typical burger and shows its assumption: "Burger (~200g patty, standard bun) — ~550 kcal"
If you say "had a big burger," it'll bump the estimate: "Large burger (~250g patty) — ~700 kcal"
The key is it always shows what it assumed — portion size, ingredients, etc. So you instantly see if it's off.
If it guessed wrong, you just correct it in the chat: "it was a smaller patty, maybe 150g" or "add cheese and bacon" — and it recalculates.
The goal was making corrections conversational instead of form-based. Feels faster than hunting through dropdowns.
Not perfect, but gets you in the right ballpark quickly. And if you want precision, you can always go detailed upfront: "200g beef patty, brioche bun, slice of cheddar, lettuce, tomato."