> For the complete documentation index, see [llms.txt](https://kizunai.gitbook.io/kizuna-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://kizunai.gitbook.io/kizuna-docs/11.-technology.md). # 11. Technology ## Technology ### Technology Built Around the Product KIZUNA's technology is designed to support one primary objective: **TURN PROJECT KNOWLEDGE INTO A USEFUL COMMUNITY EXPERIENCE.** The system connects project knowledge, the KIZUNA agent, backend infrastructure, and Telegram into one product flow. ### Core Technology Flow At a high level, the system can be represented as: **PROJECT KNOWLEDGE** ↓ **KNOWLEDGE PROCESSING** ↓ **KIZUNA AGENT** ↓ **BACKEND** ↓ **TELEGRAM** ↓ **COMMUNITY** The exact implementation of individual layers will depend on the finalized product architecture. ### Knowledge Sources KIZUNA is designed to work with project-provided knowledge from sources such as: * Project website * GitBook * Documentation * FAQs * Trusted project resources These sources provide the information foundation for the KIZUNA agent. ### AI Layer The AI layer is responsible for enabling the KIZUNA agent to understand project context and interact with community members. The exact AI model provider, model architecture, inference setup, context management, and retrieval implementation are: **\[NEEDS CONFIRMATION]** KIZUNA will document these technical components once they are finalized. ### Backend Infrastructure The current backend infrastructure decisions are: #### Supabase Supabase will be used for storage. #### Railway Railway will be used to run and deploy the backend. These components form part of the supporting infrastructure behind the KIZUNA product. ### Application Architecture The exact backend framework, API structure, authentication architecture, database schema, queue system, processing pipeline, and internal services are: **\[NEEDS CONFIRMATION]** These details should only be documented once the implementation is confirmed. ### Telegram Layer Telegram is the primary community environment for KIZUNA. The Telegram layer connects the KIZUNA experience with the community, allowing members to interact with the project-specific agent directly inside Telegram. The exact Telegram API implementation, bot architecture, permissions, and message-processing system are: **\[NEEDS CONFIRMATION]** ### Technology Principle KIZUNA's technology is not built around complexity for its own sake. Every technical component exists to support a simple product experience: **CREATE** Create the agent. ↓ **CONNECT** Connect project knowledge. ↓ **DEPLOY** Bring KIZUNA to Telegram. ↓ **ANSWER** Give the community access to project-specific information. The technology remains behind the product experience. The community simply asks questions. KIZUNA connects those questions to the project's knowledge and delivers the response. --- # 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://kizunai.gitbook.io/kizuna-docs/11.-technology.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.