> For the complete documentation index, see [llms.txt](https://docs.podtorrent.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podtorrent.com/concepts/privacy.md).

# Privacy

Short version: the node that serves your request sees it. PodTorrent's gateway doesn't keep it.

## What the gateway stores

For each request: your key id, the node, the model, the tier, the status, token counts, timings and cost. **Never** the prompt or the answer.

## What a node sees

The node's engine needs your prompt to answer it, so the node operator's machine sees both the prompt and the answer. The PodTorrent agent itself logs no content, only request ids and errors, but the operator controls their own engine and machine.

{% hint style="warning" %}
Don't send data to PodTorrent that you wouldn't share with a third-party inference provider. A confidential computing option, where even the operator can't see your data, is on the roadmap but not available.
{% endhint %}

## What PodTorrent operators see about clients

Operators see token counts, speed and earnings for their nodes, never what a request said. The one exception to anonymity is their own clients: an operator sees usage per key for clients they [brought themselves](/for-operators/own-clients.md).


---

# 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.podtorrent.com/concepts/privacy.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.
