> For the complete documentation index, see [llms.txt](https://lpc-ai-lumi.gitbook.io/lpc_ai_lumi/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lpc-ai-lumi.gitbook.io/lpc_ai_lumi/technical-implementation/core-architecture-dual-ai-agent-system.md). # Core Architecture: Dual AI Agent System The beta architecture centers on a dual AI agent system, with Lumi and Tenna working in tandem to deliver intuitive and reliable interactions. Designed for a lean deployment, the system prioritizes essential functionalities while maintaining flexibility for future enhancements, aligning with 2025 trends in lightweight AI agents for Web3. * **Lumi (Emotional Frontend Agent)**: Lumi serves as the user-facing interface, utilizing basic Natural Language Processing (NLP) based on pre-trained models (e.g., a lightweight BERT or DistilBERT variant) to interpret user queries and emotions. In beta, Lumi focuses on simplifying wallet setup and NFT interactions with conversational prompts, such as: "Let's set up your wallet like planting a seed for your digital garden!" Built with React and Web3.js for seamless wallet connectivity (e.g., Coinbase Wallet), Lumi offers a clean UI/UX with basic sentiment analysis to detect user frustration, ensuring a welcoming onboarding experience. Future iterations will expand NLP capabilities for deeper emotional engagement. * **Tenna (Logical Backend and Coordinator Agent)**: Tenna acts as the system's analytical core, managing data processing and the foundational Agent Communication Protocol (ACP). Using Node.js with minimal AI libraries for real-time analytics, Tenna handles user requests by querying on-chain data and coordinating basic agent interactions. In beta, its role is limited to simple smart contract calls and data aggregation, with plans to scale for advanced ACP orchestration. Deployed on cloud infrastructure like AWS for cost efficiency, Tenna ensures reliability with basic error handling, setting the stage for decentralized hosting in later phases. This streamlined dual-agent setup prioritizes usability and stability, addressing the beta's limited feature set while providing a robust foundation for growth. ### --- # 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://lpc-ai-lumi.gitbook.io/lpc_ai_lumi/technical-implementation/core-architecture-dual-ai-agent-system.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.