> 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/for-operators/dashboard.md).

# Operator dashboard (preview)

{% hint style="info" %}
**Preview.** The dashboard is built but not live yet. This page describes what it will show.
{% endhint %}

The operator dashboard is a private web page for operators. You sign in with your email, and you only ever see your own data. It shows counts, timings and money, never prompts or answers.

## What's on it

| Section                 | Shows                                                                                                                                                            |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Nodes**               | Each node live: connected or not, agent version, tiers, and per model the precision, slots and free slots                                                        |
| **Speed**               | Per node and model: time to first token (median and 95th percentile), tokens per second per request, peak tokens per second, and peak tokens per second per watt |
| **Tokens and earnings** | Per day, node and model: requests, tokens, earnings from matched requests, and the value of unmatched ones                                                       |
| **Your clients**        | If you [bring your own clients](/for-operators/own-clients.md): requests, tokens and billed amount per client key, and how much ran on your own nodes            |

You can look back up to 90 days.

## Tokens per watt

To see tokens per watt, declare your power draw at full load in the manifest, node-wide or per model:

```json
{ "node": "example-node-01", "power_watts": 1400, "models": [ ... ] }
```

It's only used for this figure. Support for `power_watts` arrives in the next agent release.


---

# 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/for-operators/dashboard.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.
