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

# Private Conversations

Privacy on XYNQ is **architectural**, not a setting you have to trust someone to leave switched on.

### We don't save your conversations

* Conversations are **never written to a server-side database.**
* No transcripts, no logs of message content, no analytics on what you ask.
* The model receives your conversation only for the duration needed to generate a reply, then that working state is discarded.

### Your chat lives in your browser — and only there

The only copy of your conversation is the one held in your browser tab's memory. That means:

* **Refresh the page** → the conversation is wiped, permanently.
* **Close the tab** → it's gone.
* There is no "history" to recover, by design, on any server.

### Why the network can't quietly retain content

Because inference is **sharded**, no single node ever holds your entire conversation in a form it could meaningfully store — each node sees only the slice of computation it was assigned. Combined with a no-durable-write policy in the coordination layer, retention of full conversations isn't part of the system's design.

### What this means for you

* Speak freely; nothing you type becomes a permanent record on XYNQ.
* There's no profile being built about you across sessions.
* "Private by default" is the only mode there is.

> The strongest privacy guarantee is one that doesn't depend on a promise. XYNQ is built so there's nothing to leak.


---

# 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:

```
GET https://docs.xynq.ai/privacy/private-conversations.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.