# Score every premises with your own agent

> **Casafari is the AI agent-native real estate data intelligence platform.** The most complete property index in Europe: a deduplicated, cleaned property graph of residential and commercial property, for sale and for rent, in 16 countries. Every property is one record with its full price and market history. [How the property graph is built](/docs/property-graph).

**For AI Agent Builder.** Use search_premises to identify targets and then iterate through pages using next_cursor to retrieve every match and its location figure sources.

> How can I programmatically score every premises found in a search?

MCP tool: `search_premises` (REST: POST /v1/claro/search)

## How to score premises programmatically
To ensure your agent evaluates every candidate, you must iterate through search results using pagination. Perform an initial search, and if more results exist, send the `next_cursor` as `cursor` in your next call to `POST /v1/claro/search`.

```json
POST https://platform.casafari.com/v1/claro/search
Authorization: Bearer $CASAFARI_API_KEY
{
  "brief": "commercial retail in Madrid",
  "limit": 50
}
```

You get a list of premises, each with its own data and location figures. You use the opaque `pm_` ID to retrieve full details or perform comparisons. Limits include a maximum of 200 results per page (50 if `check` is enabled).

## Related use cases

- [Nightly pipeline of premises into a CRM](https://developers.casafari.com/docs/claro/use-cases/nightly-pipeline-crm)
- [Explain any point with Location Intelligence](https://developers.casafari.com/docs/claro/use-cases/explain-point-location)
- [Keyword search from a simple form](https://developers.casafari.com/docs/claro/use-cases/keyword-search-form)
- [Compare a shortlist for a dossier](https://developers.casafari.com/docs/claro/use-cases/compare-shortlist)
- [Claro AI FAQ](https://developers.casafari.com/docs/claro/faq)