> 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/reference/glossary.md).

# Glossary

**Agent.** The `podtorrent-agent` program an operator runs next to their engine. Links the engine to the network.

**API key.** A client's secret, starting with `pt_`. Sent as a bearer token.

**Cached prompt.** A fixed conversation opening a node keeps processed. Has an id, the SHA-256 of the opening messages.

**Engine.** The operator's OpenAI-compatible inference server, such as vLLM or llama.cpp server.

**Gateway.** `api.podtorrent.com`. The single address clients call.

**Manifest.** A node's JSON description of its models, slots and prices.

**Matched.** A request whose node and network receipts agree. Only matched requests are paid.

**Node.** One operator machine or cluster connected through one agent.

**Node token.** A node's secret, used to connect to the network.

**Operator.** Someone who runs one or more nodes.

**Receipt.** A signed record of one request's token counts, made by the node and by the network.

**Slot.** Room for one request at a time on a node, for one model.

**Tier.** `interactive` (someone is waiting) or `batch` (background work).


---

# 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/reference/glossary.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.