> For the complete documentation index, see [llms.txt](https://langtech-bsc.gitbook.io/applied-intelligence/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://langtech-bsc.gitbook.io/applied-intelligence/models/decision-models/catdecide-1.md).

# CatDecide-1

A Catalan decision model that classifies, routes, scores and screens text with calibrated confidence. Coming soon.

{% hint style="warning" %}
**Coming soon.** This is a preview. Download links, usage instructions and evaluation results will be added when the model is released.
{% endhint %}

**CatDecide-1** is a decision model for **Catalan**. It reads a *state* (a message, a document, a conversation or a JSON object) and answers typed questions about it:

* **Choice:** pick one option from a list, for example which municipal service should handle a complaint.
* **Yes/no:** for example, is this message a complaint?
* **Score:** place the text on an ordered scale, for example urgency from *Low* to *Urgent*.

It doesn't generate text. It reads its answer from the probabilities it assigns to each option, which makes it fast, and those probabilities are **calibrated**: every answer comes with a confidence you can trust. Automate the confident answers and send the rest to a person.

## What it's for

* **Routing and classifying** messages and documents in Catalan public administration and services.
* **Screening** requests and replies for harmful content, in front of an [LLM](https://langtech-bsc.gitbook.io/applied-intelligence/models/text-models.md).
* **Agent decisions**, such as whether to call a tool, ask the user, or answer directly.

It is not meant for generating text, answering open questions, or making decisions about people without human oversight.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://langtech-bsc.gitbook.io/applied-intelligence/models/decision-models/catdecide-1.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
