> ## Documentation Index
> Fetch the complete documentation index at: https://developer.prove.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Build Prove with LLMs

> How Prove’s documentation is structured for machine readability and LLM-assisted integration work.

## Concepts and definitions

To better understand the technical infrastructure of Prove’s documentation, here are the key concepts and terms used:

* **Machine Readability:** The design of content in a format that can be processed and "understood" by computer programs or AI, rather than just being optimized for human visual consumption.
* **LLM (Large Language Model):** AI systems that process and generate human-like text, commonly reached through chat interfaces or APIs.

## Plain text docs

Prove designs its documentation for AI consumption. Every page maintains a parallel Markdown representation accessible via the `.md` extension—for example, [this page as Markdown](https://developer.prove.com/explanation/build-with-llm.md). That helps AI tools and agents consume Prove content.

| Feature                  | Markdown (.md)                                                                    | HTML/JS Rendered Pages                                                                 |
| :----------------------- | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- |
| **Token Efficiency**     | **High.** Minimal syntax means more actual content fits in the context window.    | **Low.** Dense with tags (`<div>`, `<span>`) and scripts that waste tokens.            |
| **Data Extraction**      | **Direct.** Content is ready to be parsed as-is without extra processing.         | **Complex.** Requires a browser engine to execute JS before content is visible.        |
| **Content Visibility**   | **Complete.** Includes all text, including content hidden in UI tabs or toggles.  | **Partial.** Hidden or "lazy-loaded" content is often missing from the initial scrape. |
| **Contextual Hierarchy** | **Explicit.** Headers (`#`, `##`) signal the importance and relationship of data. | **Inferred.** AI must guess hierarchy based on nested tags or CSS classes.             |
| **Formatting Noise**     | **Minimal.** Focuses on the data, reducing the risk of the AI getting distracted. | **Significant.** Inline styles and attributes add "noise" to the signal.               |

Prove hosts /llms.txt and /llms-full.txt files which instruct AI tools and agents how to retrieve the plain text versions of Prove pages. The /llms.txt file is an [emerging standard for making websites and content more accessible to LLMs](https://llmstxt.org/).

{/* step {"checkLink":"https://developer.prove.com/llms.txt"} */}

{/* test end */}

## Contextual menu

Plain Markdown and `/llms.txt` help tools *find* content. The harder part is getting the **page you are reading** into an assistant or agent **without fragile copy-paste**. The **contextual menu** at the top of each page is where you turn the current doc into **grounding context**: copy text, open Markdown, or connect to assistants and editor tooling.

## Model Context Protocol (MCP)

The Prove [Model Context Protocol (MCP)](https://developer.prove.com/explanation/model-context-protocol) exposes tools that AI agents can use to search Prove’s documentation and read full pages from a virtual documentation filesystem.


## Related topics

- [Set up Prove SDKs in your project](/how-to/dev-environment.md)
- [Get started with Prove API authentication](/tutorial/access-api-keys.md)
- [ProveX](/explanation/provex-overview.md)
- [Implement Prove Possession Using The Android SDK](/how-to/pre-fill-business-prove-possession-android-sdk.md)