> 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/05.-knowledge-layer.md). # 05. Knowledge Layer ## Knowledge Layer ### The Foundation of KIZUNA KIZUNA is built around a simple principle: **The better the project knowledge, the more useful the community experience can be.** Every project already has information that explains what it is, how it works, and what its community needs to know. KIZUNA connects that existing knowledge to an AI community manager. The knowledge layer is the foundation that allows KIZUNA to understand the project rather than behave like a generic AI assistant. ### Connecting Existing Knowledge Projects can connect trusted resources such as: * Project website * GitBook * Documentation * FAQs * Trusted project resources These sources provide the information that KIZUNA uses as the foundation for project-specific responses. The goal is not to create another separate knowledge base. The goal is to make the project's existing knowledge accessible through KIZUNA. ### From Documents to Conversation Traditional project knowledge usually exists as static information. A community member has to find the right page, open the documentation, and search for the answer. KIZUNA changes the interaction model. Instead of: **COMMUNITY → SEARCH → DOCUMENTATION → ANSWER** the experience becomes: **COMMUNITY → KIZUNA → PROJECT KNOWLEDGE → ANSWER** The information stays connected to its original project context while becoming accessible through conversation. ### Trusted Project Sources The quality and relevance of KIZUNA's responses depend on the knowledge connected by the project. For this reason, KIZUNA is designed around project-provided and trusted sources. The project determines which resources represent its official knowledge. These resources form the foundation of the agent's understanding of the project. ### A Living Knowledge Layer Project information can change over time. Documentation can be updated. FAQs can change. New information can be added. The exact mechanisms KIZUNA will use to detect, process, and update changes across connected sources are: **\[NEEDS CONFIRMATION]** The principle remains simple: **KEEP THE KNOWLEDGE CONNECTED.**\ **KEEP THE COMMUNITY INFORMED.** ### Knowledge and the KIZUNA Agent The knowledge layer and the KIZUNA agent work together. The knowledge layer provides the project information. The agent uses that information to interact with the community. This creates the core relationship: **PROJECT KNOWLEDGE → KIZUNA AGENT → COMMUNITY** KIZUNA does not need to replace the project's existing documentation. It makes that documentation more accessible by bringing it into the community experience. ### The Knowledge Layer in One View **PROJECT WEBSITE** **GITBOOK** **DOCUMENTATION** **FAQs** **TRUSTED RESOURCES** ↓ **KIZUNA KNOWLEDGE LAYER** ↓ **KIZUNA AGENT** ↓ **TELEGRAM COMMUNITY** The result is a direct connection between the information a project maintains and the people who need it. --- # 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/05.-knowledge-layer.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.