ChatGPT portion estimation
By Eric Parker, founder of TrueCal.
Portions are fuzzy. The best tracker makes the assumption visible, then lets you fix it in a sentence.
These examples explain how to ask an AI assistant for nutrition estimates. To save meals in TrueCal, use the TrueCal app. Its connected custom ChatGPT integration can log meals and review progress, subject to account access. It is not yet published in the ChatGPT plugin directory.
Describe what you ate, check the estimate, and save the meal in the TrueCal app. The sections below explain what to check for this topic.
Portion words
Use a weight, package serving, or household measure when you know it. Say whether the amount describes the whole dish or the portion you ate.
Assumptions
Words such as a handful or a bowl leave room for estimation. Review the assumed amount before relying on the total.
Corrections
If the portion is wrong, provide the amount you actually ate. For packaged food, include the serving size from the label.
ChatGPT portion estimation: the cheat sheet
A practical cheat sheet for portion estimation with ChatGPT: cups, slices, palm-size, restaurant portions, and the details that change calories the most.
Short answer
Portion estimation is the #1 lever for a reliable ChatGPT calorie tracker. The fastest way to improve estimates is to use consistent portion phrases like “1 cup”, “2 slices”, “palm-sized”, and to call out the high-calorie extras (oil, dressing, cheese, nuts, alcohol). When you’re unsure, ask for a range (low/typical/high) instead of a fake-precise single number.
- Cups and slices beat “a bowl” and “a plate”
- Oil, sauce, and drinks often matter more than the main food
- Use ranges when you don’t know the exact amount
Why portions matter (more than the prompt)
If you tell ChatGPT “chicken and rice,” it can only guess. If you tell it “6 oz chicken, 1 cup rice, 1 tbsp olive oil,” it has something to work with. Most “accuracy” problems come from missing amounts, not the AI being bad at nutrition tables.
The fastest portion formats (ranked)
- Best: measured units (cups, tbsp, oz, grams)
- Great: countable units (slices, eggs, tortillas, scoops)
- Good enough: hand-based units (palm, fist, thumb, handful)
- Last resort: “small/medium/large” plus context
Copy-paste prompt for “range” estimates
Estimate calories and macros (protein, carbs, fat). Meal: [what I ate] Portions: [rough amounts] Details: [brand/recipe/cooking method, sauces, oils, drinks] Output: 1) Low / typical / high estimate 2) Biggest uncertainty 3) The one detail I should specify next time
For the full workflow, start here: ChatGPT calorie tracker.
Portion phrase cheat sheet
Carbs
- Rice/pasta/oats: “1 cup cooked”, “2 cups cooked”
- Bread: “2 slices”, “1 bagel”, “1 tortilla”
- Potatoes: “1 medium”, “a fist-sized”
Protein
- Meat/fish: “palm-sized”, “about 6 oz”
- Eggs: “2 eggs”, “3 eggs”
- Beans: “1/2 cup”, “1 cup”
Fats (easy to undercount)
- Oil/butter: “1 tbsp”, “2 tbsp”, “buttered”
- Dressing: “1 tbsp”, “2 tbsp”, “on the side”
- Nuts/nut butter: “a handful”, “1 tbsp”
Restaurant portions (the honest approach)
Restaurants vary. The best you can do is describe the item, the size, and the add-ons. If you split it, say “ate half.” For restaurant-specific prompts and examples: ChatGPT calorie tracker for restaurants.
Two small habits that improve accuracy a lot
- Learn 5 “anchor” portions you eat often (rice, pasta, chicken, oil, dressing) once, then reuse that mental model.
- Always call out the multipliers (oil, sauce, cheese, drinks) even when you skip the exact measurement.