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

# Midas AI

Midas AI is the chat and reasoning layer that answers market questions, reads account context, explains positions, and prepares user-confirmed actions.

* **Ask questions** — Ask about assets, positions, recent transactions, balances, market narratives, or specific trade ideas.
* **Prepare actions** — Midas can draft swaps, perps, deposits, withdrawals, limit orders, and other pending confirmations.
* **Use live context** — The chat context includes portfolio snapshots, per-chain cash, open perps, recent transactions, and page context.

## Capabilities

Midas AI shortens the path between a question and an informed action. It can summarize market context, inspect account state, explain trades, and prepare structured order drafts.

* Explain token or perp movement using page context and The Wire.
* Compare holdings and answer portfolio questions.
* Prepare executable actions only when inputs can be resolved safely.

## Context sources

Midas AI is grounded by the same product context visible to the user: portfolio, cash breakdown, positions, recent transactions, selected assets, price history, signals, and conversation state.

## Confirmation model

Executable AI output becomes a pending action. The user reviews the card, route, amount, side, destination, and risk details before confirming.

{% hint style="info" %}
**No silent defaults**

If Midas cannot determine a transaction-critical value, it should ask for clarification or fail instead of guessing.
{% endhint %}


---

# 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.midasmarkets.xyz/platform/midas-ai.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.