> For the complete documentation index, see [llms.txt](https://docs.aviator.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aviator.co/manage/security/aviator-agents-data-usage-and-retention-policy.md).

# Aviator Agents Data Usage & Retention Policy

## **Models Used**

We primarily use **Claude Sonnet 3.7** for LLM-based tasks internally. While other models may be evaluated in the future, our primary dependency is on Claude Sonnet 3.7.

## **Data Retention Policy**

* We **do not** save the code generated during a migration.
* We **do** retain chatbot conversation history for 1 year. Not applicable for on-prem.
* No user data or generated code is used for retraining or fine-tuning models.
* Logs are maintained for compliance and monitoring but we do not store code snippets. Logs are retained for 30 days.

## **Data Usage & Security Guidelines**

1. **No Training on User Data**
   * We ensure that our LLM does **not** use user-provided inputs for training.
   * Conversations and code shared are **not incorporated** into model updates or fine-tuning.
   * More info: [Anthropic’s API Data Retention Policy](https://privacy.anthropic.com/en/articles/7996875-can-you-delete-data-that-i-sent-via-api)
2. **Copyrighted Code Assurance**
   * The latest version of the Claude API offers a copyright assurance similar to that of GitHub Copilot
     * Customers have ownership rights to generated output and legal protection against copyright claims to AI generated code.
     * More info: [Anthropic’s Copyrighted Code Assurance Policy](https://www.anthropic.com/news/expanded-legal-protections-api-improvements)


---

# 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 dynamically by asking a question.

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

```
GET https://docs.aviator.co/manage/security/aviator-agents-data-usage-and-retention-policy.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.