> For the complete documentation index, see [llms.txt](https://docs.rainbird.ai/rainbird/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rainbird.ai/rainbird/rae/validate-the-decision-model.md).

# Validate the decision model

What a completed build includes, and how to check that it captures your brief.

## Review build results

When a build completes, Rae creates a new model version. The project shows the current version, its tests, endpoint, knowledge, and a link to open the model in Studio.

The completion summary explains what the model decides, the information it needs, and the result it produces. It also records what changed from the previous version.

### Tests must pass

Rae runs every delivered test against the completed model before finishing the build.

If a test fails, the agent returns to the relevant work, fixes the issue, and reruns the full test suite. After five attempts, the build pauses and lists the failing tests for you to review.

A build never completes with a failing test.

### What to check first

1. **Read the documentation.** It explains the model's logic, identifies the relationship to query, and records any decisions the agent made when details were unclear.
2. **Check the coverage map.** The requirement-to-rule map confirms whether the model includes each rule, threshold, and exception from your brief.
3. **Run the tests, then add your own cases.** Start with the delivered test suite. Then test the boundary cases you know about.
4. **Check what Rae read.** For large documents, the completion summary states how much was read. The documentation identifies any sections that were not used.

### Find build outputs

The project's **Files** view contains the decision models XML, documentation, and Studio test file.

If you requested tuning, the project also includes a performance report. You can download the build transcript and the other files produced during an update from the project.

### Open in the Studio

The decision model can be opened in the Studio, which is a modelling environment designed for Knowledge Engineers. This provides an ability to view a graph visualisation of the model, displaying the ontology, underlying data and rules.

More information about the Studio can be the [Studio](https://docs.rainbird.ai/rainbird/studio/overview.md) section.


---

# 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://docs.rainbird.ai/rainbird/rae/validate-the-decision-model.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.
