From a purchase order to an impact estimate
Every procurement file goes through the same three stages. The Notebook handles the transitions between them automatically, writing an intermediate file at each step so you can inspect, if necessary correct, and re-run without starting over.
Identify ingredients and their weights
Each product line, e.g., "SOUP, CHICKEN NOODLE RTU LOW SODIUM," 21.8 lbs — is broken into its likely constituent ingredients (water, chicken broth, cooked chicken, noodles, vegetables), each with an estimated share of the product's total weight.
Reads: your procurement .csvitem_weights.json → Writes: ingredients_{file}.csv
Sort each ingredient into a shared category
Every ingredient is assigned to one of about 125 categories — beef, dairy cheese, tilapia
(farmed), wheat/rye, unidentified meat, and so on. The code first checks foodcategories.json which pairs ingredients with categories;
if an ingredient isn't already listed there, it asks the AI model for a category and records the new
pairing for you to review later for possible inclusion in the foodcategories.json file.
Reads: ingredients_{file}.csvfoodcategories.json → Writes: categories_{file}.csv
Apply conversion factors to calculate impact
The total weight in each category is multiplied against a table of per-pound (or per-kilogram) factors — calories, CO₂e, carbon opportunity cost, direct and indirect animal lives, water withdrawals, land use, and eutrophication — to produce the final totals.
Reads: categories_{file}.csvfactors.csv → Writes: impacts_lbs_{file}.csvimpacts_metric_{file}.csv
One row, followed all the way through
Consider one row of a 1780 row procurement file that lists 21.8 pounds of "SOUP, CHICKEN NOODLE RTU LOW SODIUM." Stage 1 may resolve it like this:
| Ingredient | Category | Share | Weight |
|---|---|---|---|
| water | water | 50% | 10.90 lbs |
| chicken broth | liquids | 20% | 4.36 lbs |
| cooked chicken meat | chicken | 10% | 2.18 lbs |
| noodles | grains | 10% | 2.18 lbs |
| carrots | vegetables | 5% | 1.09 lbs |
| celery | vegetables | 4% | 0.87 lbs |
| onions | vegetables | 1% | 0.22 lbs |
Once all the multi-ingredient items in the file have gone through the same process, Stage 3 sums each category's weight across the entire procurement file and reports totals like these (an excerpt):
| Category | Weight | CO₂e | Total animal lives |
|---|---|---|---|
| chicken | 148,246 lbs | 652,282 lbs | 44,689 lives |
| beef | 41,449 lbs | 1,713,781 lbs | 51.3 lives |
| butter | 9,796 lbs | 109,170 lbs | 1.0 life |
| apples | 6,799 lbs | 2,434 lbs | 0 lives |
It holds up across languages
As an experiment, the project's authors translated all 1,500+ products in a US Foods procurement file into French, Spanish, and German, then ran the unaltered Notebook against the translated list. Total impact figures differed by less than 2% per category compared to the English run.
Ready to run it on your own file?
The Get started page covers both the local Notebook route and the hosted web tool, plus how to reshape a vendor spreadsheet into a format the code recognizes.