# Reading path

**Start with the national herd, end with an agent: nine notebooks, nineteen departments, one glossary.**

cow-tools is Sophia's proof of concept: everything Uruguay publishes about its livestock, as a graph agents and people can question, with the provenance of every number. *Why would anyone want to know so much about… Uruguay?*

## The notebooks, in order

1. [**The national herd at a glance**](https://cow-tools.sophia-labs.com/guide/notebook-national-herd/index.md): Uruguay's holders declared 12,265,269 cattle on 30 June 2025 (11,583,321 beef and 681,948 dairy) and 4,799,066 sheep. On 2024, cattle changed +1.05% and sheep -11.47%.
2. [**Cattle and sheep, department by department**](https://cow-tools.sophia-labs.com/guide/notebook-cattle-and-sheep/index.md): Only Salto and Artigas still have more sheep than cattle by heads (53.5% and 51.9% sheep). The national flock fell 11.5% in one year, from 5,420,661 to 4,799,066: 621,595 fewer sheep.
3. [**Dairy country**](https://cow-tools.sophia-labs.com/guide/notebook-dairy-country/index.md): Florida, San José, Colonia produce 68.3% of Uruguay's milk (2,298.4 million litres in 2025, +1.67% on 2024). Florida makes the most: 26.5%.
4. [**Breeders in the east, finishers in the west**](https://cow-tools.sophia-labs.com/guide/notebook-herd-structure/index.md): Maldonado is the most breeding-heavy department: 71.7% of its beef herd is breeding cows and calves. Soriano leans hardest to finishing: 29.8% steers and fattening cows. The east breeds; the west finishes.
5. [**How hard the land is stocked**](https://cow-tools.sophia-labs.com/guide/notebook-stocking-intensity/index.md): Uruguay carries 0.856 cattle per hectare of livestock land (12,265,269 cattle on 14.32 million ha). The densest department, San José, carries 1.67; the sparsest of the big grazing departments, Artigas, 0.65.
6. [**One year on, 2024 to 2025**](https://cow-tools.sophia-labs.com/guide/notebook-year-over-year/index.md): Between the 2024 and 2025 declarations Uruguay gained 127,121 cattle (+1.05%) and lost 621,595 sheep (-11.47%), while the number of holders declaring beef cattle went from 61,561 to 59,121 (-4.0%): more cattle, fewer hands.
7. [**The herd ledger**](https://cow-tools.sophia-labs.com/guide/notebook-herd-ledger/index.md): Uruguay's cattle books balance only if 2,300,543 head left the farms between the 2024 and 2025 declarations: 18.95% of the opening herd. Calves born (2,697,988) outran deaths (247,498), home slaughter (22,826) and the herd's own growth (+127,121).
8. [**Finding other Uruguay data**](https://cow-tools.sophia-labs.com/guide/notebook-finding-other-data/index.md): Against the 2011 census (the latest by department in the catalogue's file), Uruguay has 3.73 cattle per person. In Durazno it is 16.7; in Montevideo, 0.0021. The dataset was found by meaning in the catalogue graph, fetched from the link its DCAT record gives, and joined on the department codes.
9. **Ask the agent** *(unexecuted)* ([`notebook-ask-the-agent`](https://cow-tools.sophia-labs.com/guide/notebook-ask-the-agent/index.md)): Start a personal agent over the herd data from Python, with your own OpenRouter key, and check its answer against the cube.

## The departments

| department | cattle 2025 | sheep 2025 | milk share | document |
| --- | --- | --- | --- | --- |
| Florida | 1,117,097 | 202,434 | 26.5% | [`department-florida`](https://cow-tools.sophia-labs.com/guide/department-florida/index.md) |
| Tacuarembó | 1,061,136 | 398,742 | 0.2% | [`department-tacuarembo`](https://cow-tools.sophia-labs.com/guide/department-tacuarembo/index.md) |
| Durazno | 952,171 | 290,920 | 9.2% | [`department-durazno`](https://cow-tools.sophia-labs.com/guide/department-durazno/index.md) |
| Cerro Largo | 950,412 | 303,495 | 0.2% | [`department-cerro-largo`](https://cow-tools.sophia-labs.com/guide/department-cerro-largo/index.md) |
| Salto | 898,899 | 1,032,181 | 0.9% | [`department-salto`](https://cow-tools.sophia-labs.com/guide/department-salto/index.md) |
| Paysandú | 801,512 | 555,079 | 2.3% | [`department-paysandu`](https://cow-tools.sophia-labs.com/guide/department-paysandu/index.md) |
| Artigas | 742,198 | 801,403 | 0.0% | [`department-artigas`](https://cow-tools.sophia-labs.com/guide/department-artigas/index.md) |
| Rocha | 682,644 | 154,813 | 0.5% | [`department-rocha`](https://cow-tools.sophia-labs.com/guide/department-rocha/index.md) |
| Lavalleja | 654,451 | 261,086 | 0.6% | [`department-lavalleja`](https://cow-tools.sophia-labs.com/guide/department-lavalleja/index.md) |
| Rivera | 639,917 | 182,585 | 0.2% | [`department-rivera`](https://cow-tools.sophia-labs.com/guide/department-rivera/index.md) |
| Treinta y Tres | 584,734 | 178,572 | 0.2% | [`department-treinta-y-tres`](https://cow-tools.sophia-labs.com/guide/department-treinta-y-tres/index.md) |
| Soriano | 567,452 | 55,293 | 5.8% | [`department-soriano`](https://cow-tools.sophia-labs.com/guide/department-soriano/index.md) |
| Río Negro | 549,369 | 69,144 | 3.6% | [`department-rio-negro`](https://cow-tools.sophia-labs.com/guide/department-rio-negro/index.md) |
| San José | 541,254 | 37,781 | 22.6% | [`department-san-jose`](https://cow-tools.sophia-labs.com/guide/department-san-jose/index.md) |
| Colonia | 537,066 | 38,341 | 19.2% | [`department-colonia`](https://cow-tools.sophia-labs.com/guide/department-colonia/index.md) |
| Flores | 409,429 | 83,001 | 2.5% | [`department-flores`](https://cow-tools.sophia-labs.com/guide/department-flores/index.md) |
| Canelones | 338,601 | 50,487 | 4.9% | [`department-canelones`](https://cow-tools.sophia-labs.com/guide/department-canelones/index.md) |
| Maldonado | 234,191 | 101,340 | 0.6% | [`department-maldonado`](https://cow-tools.sophia-labs.com/guide/department-maldonado/index.md) |
| Montevideo | 2,736 | 2,369 | 0.0% | [`department-montevideo`](https://cow-tools.sophia-labs.com/guide/department-montevideo/index.md) |

## The guide

- [*Finding other Uruguay data*](https://cow-tools.sophia-labs.com/guide/finding-other-uruguay-data/index.md)
- [*How to read the cubes*](https://cow-tools.sophia-labs.com/guide/reading-the-cubes/index.md)
- [*Known caveats*](https://cow-tools.sophia-labs.com/guide/caveats/index.md)
- [*Questions with exact answers*](https://cow-tools.sophia-labs.com/guide/questions-with-exact-answers/index.md)
- [*What DICOSE is*](https://cow-tools.sophia-labs.com/guide/what-is-dicose/index.md)

## Reference

- [`glossary-dicose`](https://cow-tools.sophia-labs.com/guide/glossary-dicose/index.md): DICOSE, census areas, PD_AD and PD_PF, the categories, the cube.
- [`how-to-ask-this-data`](https://cow-tools.sophia-labs.com/guide/how-to-ask-this-data/index.md): MCP, SPARQL and Python, with examples run at build time.

Everything here is also on the web: https://cow-tools.sophia-labs.com/ (the notebooks are listed on the front page).

## Connected (the graph's wires)

- Next in the reading path: [The national herd at a glance](https://cow-tools.sophia-labs.com/guide/notebook-national-herd/index.md)

---

This document is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), credit "cow-tools, Sophia Labs"; the data it describes keeps its own licence (Uruguay's open-data licence).

The cow-tools guide, Start here: https://cow-tools.sophia-labs.com/guide/reading-path/ (this page for people) · the whole guide: https://cow-tools.sophia-labs.com/guide/index.md · in Sophia: the graph `cow-tools-guide`, document `reading-path` (MCP `read_document` at https://cow-tools.sophia-labs.com/mcp). CC BY 4.0, credit "cow-tools, Sophia Labs".