# LLMs.txt

ETH Strategy provides an `llms.txt` file — a machine-readable protocol overview designed for consumption by large language models, AI agents, and automated tools.

## What is llms.txt?

The `llms.txt` standard provides a structured, plain-text summary of a project that AI models can use to understand the protocol without parsing an entire documentation site. It covers:

* **Core concepts** — what esETH, STRAT, CDT, and ESPN are and how they relate
* **Mechanics** — how bonding, conversion, staking, and lending work
* **Contracts** — all deployed addresses on Ethereum mainnet and Derive chain
* **Governance** — what's tunable, what's immutable, who controls what
* **Risks** — honest assessment with mitigations
* **Instructions for AI** — explicit guidance on common points of confusion

## Access

The file is available at the root of the documentation repository:

```
/llms.txt
```

## Why This Matters

AI agents are increasingly used to research, compare, and interact with DeFi protocols. Providing structured, accurate data in a format optimized for LLM consumption ensures that:

1. AI-generated answers about ETH Strategy are accurate
2. Agent-based systems can integrate with our protocol correctly
3. Automated research tools can index our protocol alongside others

## For Autonomous Agents

If you are building an AI agent that queries on-chain state, submits transactions, or provides structured data about ETH Strategy, see the dedicated [AI Agents](/developers/ai-agents.md) page. It provides:

* Function selectors for direct RPC calls (no ABI required)
* Typed protocol state schema
* Machine-readable token metadata and governance parameters in JSON
* Safety rules for transaction agents
* Derived metric formulas (EPS, mNAV, protocol leverage, ESPN APY)

The `llms.txt` file is for understanding; the AI Agents page is for operating.

## Keeping It Current

The `llms.txt` file is updated alongside protocol documentation. When new contracts deploy or mechanics change, the file is revised to reflect the current state of the protocol.


---

# Agent Instructions: 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:

```
GET https://docs.ethstrat.xyz/references/llms.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.