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

# llms.txt

## llms.txt

These docs are published in two LLM-friendly formats following the [llmstxt.org standard](https://llmstxt.org). Point any LLM tool at either URL.

| File                | URL                                                                                | Use when                                                                                                |
| ------------------- | ---------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| **`llms.txt`**      | [`docs.panora.exchange/llms.txt`](https://docs.panora.exchange/llms.txt)           | You want a **structured index** — page titles, descriptions, links. The LLM follows the links it needs. |
| **`llms-full.txt`** | [`docs.panora.exchange/llms-full.txt`](https://docs.panora.exchange/llms-full.txt) | You want the **entire docs corpus** inline. Best for deep RAG and offline ingestion.                    |

### Per-page markdown

Every page on docs.panora.exchange is also available as raw markdown — append `.md` to any URL:

```
https://docs.panora.exchange/developer/swap/sdk.md
https://docs.panora.exchange/product-suite/dca.md
```

Or send the request with `Accept: text/markdown`.

### How to use

#### ChatGPT / Claude.ai

> Read <https://docs.panora.exchange/llms-full.txt> and answer questions about Panora.

#### Custom GPT / Claude Project instructions

> Reference the Panora docs at <https://docs.panora.exchange/llms.txt> — fetch the linked pages as needed.

#### RAG pipeline

```bash
curl https://docs.panora.exchange/llms-full.txt > panora-docs.md
# Chunk, embed, and index with your tool of choice.
```

### Why this matters

LLMs work better with Markdown than HTML — higher signal density, no nav/footer/script noise eating context. Pointing your agent at `llms-full.txt` instead of scraping HTML cuts token usage by roughly 80%.

### Auto-generated

Both files regenerate automatically whenever a docs page changes. Zero maintenance — the page descriptions you see on the live site are what populate `llms.txt`.

### Related

* Agent Skills — structured playbooks layered on top of these docs.
* MCP Servers — for live, queryable access to the same content.


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.panora.exchange/ai/llms.txt.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.