# LLM used on Structural Cloud

For its AI-enhanced features, Structural Cloud uses Opus 4.6, Sonnet 4.5, and Haiku 4.5 deployed on [Microsoft Foundry](https://azure.microsoft.com/en-us/products/ai-foundry).

## How information is used by the LLM <a href="#llm-information-use" id="llm-information-use"></a>

Our usage of information follows the [Anthropic usage policy](https://www.anthropic.com/legal/aup).

Your input prompts and generated outputs remain private. They are never used to train the underlying models. However, as a best practice, we recommend that you do not include highly sensitive values in your manual prompts.

To deliver high-quality suggestions, Structural sends to the model as context:

* Your database schema.
* By default, representative data samples. However, you can [configure Structural to exclude the sample data](https://docs.tonic.ai/app/admin/configuring-the-use-of-ai-features#llm-detection-exclude-sample-data).

For answers to more detailed questions, reach out to our support team.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.tonic.ai/app/admin/structural-ai-use/llm-used-on-structural-cloud.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.