# What ORACLE Does

![ORACLE — AI risk scanner + chat](/files/vuGnY19dPOrny4K9jYhC)

ORACLE is Snake OS's built-in AI assistant + Solana token risk scanner. Two modes in one app:

## Mode 1: Token Risk Scan (Free + Unlimited)

Paste any Solana token contract address (CA) into the chat box → ORACLE returns a structured risk report:

* ✅/⚠/✗ **Verdict** (SAFE / CAUTION / RISKY / LIKELY RUG)
* **Risk score** (0–100)
* **Market cap**, **liquidity**, **24h volume**
* **Flags** — concrete warning signals (top-10 holder %, low liquidity, mint authority active, freeze authority active, etc.)
* All powered by trustfi + DexScreener data

**This path is UNMETERED.** Paste-CA scans are free and unlimited. No per-message cost.

## Mode 2: Free-Form Chat (Metered)

Ask ORACLE general questions — Solana ecosystem, memecoin trading concepts, Snake OS feature questions, anything not tied to a specific CA.

This path uses Gemini 2.5 Flash (with DeepSeek V3 fallback) and **does cost real AI tokens**, so it's rate-limited:

* **20 requests per minute** per IP (anti-burst)
* **40 messages per day per wallet** (personal cap)
* **2000 messages per day globally** (hard ceiling so IP-rotation abuse can't run the bill past \~$1-2/day)

These limits are cost-control, not monetization. Token scans stay free + unlimited even if you hit your chat cap.

## When to Use Which

* "Is this CA a rug?" → paste the CA → instant scan (free)
* "What does 'mint authority' mean?" → free-chat question (metered)
* "What do you think of XYZ memecoin's chart?" → free-chat question (ORACLE will redirect you to MARKET WATCH or risk-scan via CA paste)


---

# 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.snake-os.com/oracle-ai-risk-scanner/overview.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.