---
title: For AI and agents
description: This documentation as Markdown — an index, the whole corpus in one document, every page addressable as its own source, and a control that puts a ready-made prompt on the clipboard.
keywords: llms.txt, llms-full.txt, markdown, agent, ai, machine-readable, prompt, copy for ai
group: resources
---

## The two documents {#llms-txt keywords="llms.txt, llms-full.txt, markdown, agent, index"}

Running an agent? This site publishes itself. [/llms.txt](https://documentation.kumorouter.com/llms.txt) is the index of this documentation in the llms.txt convention — one top-level title, a one-line summary, then the pages — which is a shape any agent can rely on without being taught this site in particular.

[/llms-full.txt](https://documentation.kumorouter.com/llms-full.txt) is the other half of the same idea: every authored page of this documentation as one Markdown document, in the order the site lists them, followed by a live index of the model catalog — each model's name and its own address, not the body of its page. It is what to fetch when the agent is going to answer questions rather than look one thing up, and it costs a fraction of the tokens that reading the rendered HTML would.

Both are assembled from the same pages the site itself renders from, so neither can drift into being a stale second copy of the product. The index draws on the title and summary each page declares, the full document on the whole of each page’s text — both in the build that changes the pages themselves.

## Any page as Markdown {#raw-markdown keywords="raw, .md, source, copy, clipboard"}

Every page of this site is also addressable as its own Markdown source.

- **The rule.** Append `.md` to the page's path and the answer is the Markdown this page was rendered from, with this deployment's addresses already filled into it — the quickstart, for example, is served as Markdown at its own address with `.md` on the end, and the hostnames in its examples are the ones you would actually call.
- **The exception.** The home page is the one address the rule does not fit — it is served at `/index.md`, because `/.md` is not a name.
- **Links.** Links from one page of this site to another stay in the site's own `page:` form rather than becoming URLs, so the client that fetched the page can tell an internal reference from an address it should follow.

When an agent needs a single topic and not the whole corpus, fetch that page's own `.md`, not the home page.

### Copy for AI

Every article header carries a row of actions, and the first of them is **Copy for AI**. It puts on the clipboard not the page's text but a finished prompt around it. The prompt has four parts:

- a short preamble in the language you are reading — what Kumo is, which page this is, and the address it lives at;
- the page's own Markdown with the model already filled in;
- a pointer to [/llms-full.txt](https://documentation.kumorouter.com/llms-full.txt) for when one page is not enough;
- an empty "My question:" line at the end.

Paste it into a conversation with an assistant and write your question underneath: the context is already assembled, and assembled from the very page you are reading.

Beside it are two plainer actions. Copy as Markdown puts on the clipboard exactly the document the `.md` address serves — the same text, for pasting into a conversation rather than fetching over the network. The link next to it opens that address itself.

## Point an agent at it {#agent-prompt keywords="prompt, agent, assistant, instruction"}

:::prompt
Hand this to a coding assistant before you ask it anything about Kumo. It is English-only by design — that is how coding assistants follow an instruction most reliably.

```text
Read https://documentation.kumorouter.com/llms-full.txt before answering anything about Kumo.

It is the whole of this documentation as one Markdown document: what the product
is, how a key is issued, how a request is shaped, what comes back, and what a
refusal looks like. Prefer it over crawling the rendered site — it is the same
information at a fraction of the tokens, and it is generated from the site's own
pages rather than written twice.

Any single page is also available as Markdown: take the page's address, drop any
#fragment from it, and add .md. The home page is the exception and is served at
/index.md.

The authored pages themselves name no model ID and no price: they carry a <model>
placeholder wherever one would go. llms-full.txt appends a live index of the model
catalog after them — each model's name and its own address, not its body — so read
that index, or the live catalog and pricing endpoints it points to, for those
values, and do not invent one.
```
:::

> [Every operation, member by member →](/en/api-reference)