> For the complete documentation index, see [llms.txt](https://agents-organization-5.gitbook.io/echelon-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agents-organization-5.gitbook.io/echelon-ai/core-functionality/use-cases.md). # Use Cases #### **Use Cases** **Leveraging Prism AI Agent for Advanced Insights into the Crypton/MemeCoin Ecosystem** *** #### **1. Initiating Queries and Intelligent Task Allocation** Users can submit queries via the DApp, specifying their desired analysis—such as evaluating a MemeCoin’s market dynamics. The **Router Module** parses these inputs and delegates tasks to the most suitable agents (e.g., Market Agent, Media Agent). This intelligent task allocation ensures users focus on their goals while the complexity is abstracted away. *** #### **2. Single-Agent Analytical Workflow** For simpler queries, a **Single Agent** can handle the request efficiently through the following workflow: **Step 1: Intent Detection and Task Decomposition** * The agent interprets the user's objective and breaks it into smaller, manageable tasks such as retrieving market trends or monitoring social sentiment. **Step 2: Functional Execution and Data Retrieval** * Blockchain or social media APIs (e.g., Solana, Twitter, Telegram) are used to gather real-time data. **Step 3: Data Summarization via LLM** * Using advanced language models, raw data is synthesized into actionable insights, delivering concise and user-friendly outputs. *** #### **3. Multi-Agent Collaborative Intelligence** For more complex analyses, the **Multi-Agent Module** orchestrates collaborative workflows: **Step 1: Task Planning** * The **Planner Module** structures multi-phase execution flows, such as sequentially examining market dynamics, community activities, and blockchain data. **Step 2: Execution and Observation** * Agents (e.g., Market Agent, Media Agent) work in parallel to retrieve datasets. Insights from earlier phases dynamically guide subsequent steps. **Step 3: Iterative Feedback and Clarifications** * The system refines outputs through iterative loops, adjusting insights in response to user feedback or new data streams. *** #### **4. Comprehensive Analysis and Feedback Delivery** Prism AI integrates the results from multiple agents into a unified, multi-dimensional insight report. Key elements include: * **Market Dynamics:** Detailed token price trends, trading volume metrics, and volatility analysis. * **Community Pulse:** Engagement levels and sentiment analysis from platforms like Twitter and Telegram. * **On-Chain Metrics:** Token holder growth, liquidity analysis, and transaction flow summaries. *** #### **5. Real-World Application** **Scenario: Evaluating a MemeCoin’s Ecosystem Performance** **Objective:**\ Analyze the overall health and activity of a specific MemeCoin project. **Execution:** * **Market Data Extraction:** The **Market Agent** retrieves trading patterns, price fluctuations, and volume metrics. * **Community Monitoring:** The **Media Agent** analyzes Telegram discussions and Twitter mentions for sentiment and engagement trends. * **On-Chain Analysis:** Blockchain data is processed to reveal token distribution and liquidity movement patterns. **Final Insights:**\ “The analysis indicates the project has an 85% on-chain health score, with community engagement increasing by 10% and trading volume up by 32% over the past two hours.” *** #### **Empowering Users with Actionable Insights** Prism AI leverages its **advanced multi-agent framework** to deliver deep, actionable insights. By combining data from multiple dimensions—market trends, community engagement, and on-chain analysis—Prism AI ensures users make precise, informed decisions in the fast-paced and dynamic crypto ecosystem. --- # 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://agents-organization-5.gitbook.io/echelon-ai/core-functionality/use-cases.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.