> 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/09.-security-and-trust.md).

# 09. Security & Trust

KIZUNA is built around trusted project knowledge, clear information sources, and responsible handling of community interactions.

## Security & Trust

### Trust Starts With the Source

KIZUNA's responses are built around the knowledge provided by the project.

Projects can connect their website, GitBook, documentation, FAQs, and other trusted project resources.

This creates a clear foundation for the information used by the KIZUNA experience.

The core principle is:

**TRUSTED PROJECT KNOWLEDGE → KIZUNA → COMMUNITY**

### Project-Controlled Knowledge

KIZUNA is designed to work with project-specific information rather than relying only on generic knowledge.

The project determines the resources that represent its official information.

This helps establish a clear relationship between:

**PROJECT**

and

**PROJECT KNOWLEDGE**

and

**KIZUNA**

### Clear Information Boundaries

KIZUNA should represent the project based on the information connected to it.

It should not be presented as a source of information beyond the project's provided knowledge without appropriate confirmation.

The exact mechanisms used to enforce knowledge boundaries and handle unsupported questions are:

**\[NEEDS CONFIRMATION]**

### Data & Infrastructure

KIZUNA currently plans to use:

**Supabase**\
For storage.

**Railway**\
For running and deploying the backend.

The exact data architecture, encryption approach, authentication system, access controls, data retention policies, and privacy implementation are:

**\[NEEDS CONFIRMATION]**

### AI Reliability

AI-generated responses can depend on the quality and completeness of the information available to the system.

For KIZUNA, the connected project knowledge is therefore an important part of the overall experience.

The exact methods used to evaluate response accuracy, handle conflicting sources, prevent unsupported answers, and monitor AI performance are:

**\[NEEDS CONFIRMATION]**

KIZUNA will document these mechanisms as the underlying implementation is finalized.

### A Transparent Product Approach

KIZUNA is designed around a simple principle:

**USE PROJECT KNOWLEDGE TO SUPPORT THE PROJECT COMMUNITY.**

Rather than making unsupported claims about accuracy, security, or performance, KIZUNA's technical and security practices should be documented based on the actual implementation.

This keeps the product documentation clear, transparent, and verifiable.


---

# 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/09.-security-and-trust.md?ask=<question>&goal=<endgoal>
```

`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.