> For the complete documentation index, see [llms.txt](https://coinrotator.gitbook.io/coinrotator-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://coinrotator.gitbook.io/coinrotator-docs/shumi-agent-your-ai-quant.md). # Shumi Agent (Your AI Quant) ### What is Shumi? {% embed url="" %} **Shumi** is an AI-driven trading assistant built on CoinRotator's infrastructure, designed to help crypto traders navigate markets through natural language interactions. The platform combines trend analysis, sentiment tracking, liquidity data, and confluence signals into a conversational interface. While CoinRotator provides the raw trend engine and analytical tools, **Shumi serves as your intelligent guide**, interpreting data and offering context-aware trade insights, coin evaluations, and portfolio support. ***
### How It Works Shumi utilizes structured internal prompts to interpret: * Weekly, daily, and 4H trend data across 3,000+ tokens (on-chain & CEX) * CoinRotator filters (band levels, streaks, futures data) * Market health indicators * Social sentiment integration for trend strength determination * Advanced futures and sentiment data through natural language requests The system updates daily and operates within constrained logic boundaries to minimize hallucinations and ensure outputs remain grounded in actual market structure. ***
### 🧠 Prompt Architecture Shumi employs a modular prompt system where each user archetype (e.g., "Signal Seeker," "Risk Mapper") routes through different configurations based on request context. **Prompt inputs include:** * Coin trends and category performance * Market health + BTC trend * Sentiment streams (planned enhancement) * User-defined filters (HMA slope, bar streaks) **Prompt outputs feature:** * Clear markdown tables for trends * Price data with timestamps * Trade-ready outputs: entries, invalidations, and exits * Internal links to coin pages on [CoinRotator.app](https://coinrotator.app/) *** ### 🧬Classifier & Archetypes Each user request is parsed through a **classifier layer** determining intent: * Trade opportunity search * Narrative performance inquiry * Risk condition assessment Shumi responds using matched archetype logic, creating an adaptable system with multiple specialized personalities. **Current archetypes:** * Signal Seeker (trend-focused) * Risk Mapper (macro-focused) * Alpha Hunter (sentiment + rotations) * Lore Keeper (journal + trade logs) * Narrative Navigator (meme/sector flow alignment) Future archetype customization will be available to SHUMI token stakers.
*** ### Virtuals Protocol & Token Integration Shumi is integrated with [Virtuals Protocol](https://app.virtuals.io/geneses/6667) as **$SHUMI**, providing tokenized access within the Agent Commerce Protocol (ACP) ecosystem. Operating as a data provider within the agentic economy, Shumi streams high-conviction market insights to other agents while on-chain alignment mechanisms ensure value distribution to contributors. **Key mechanics:** * **Mindshare rewards** for contributors expanding the tool or prompt system * Enhanced features through SHUMI token staking * On-chain reputation and usage tracking linked to wallet addresses Check Discord or Telegram for periodic mindshare mining campaigns. ***
### ACP Agent Marketplace Shumi features native support for the **Agent Communication Protocol (ACP)**, enabling seamless cooperation with other agents in the [Virtuals Protocol](https://app.virtuals.io/) ecosystem. Test Shumi directly through Agent Butler: We believe Shumi provides one of the most **reliable and structured trend-following signal sources** available to agents in the ACP marketplace. Its access to CoinRotator's comprehensive dataset—combined with internal filtering logic and sentiment integration—makes it ideal for: * Contributing directional bias and risk context to trading agents * Supporting multi-agent workflows for trade discovery and filtering * Acting as a composable module in strategy-specific pipelines Shumi is live on ACP and ready for agent message interactions, with broadcast capabilities under development for enhanced autonomous operation. --- # 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://coinrotator.gitbook.io/coinrotator-docs/shumi-agent-your-ai-quant.md?ask=&goal= ``` `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.