> For the complete documentation index, see [llms.txt](https://hyperdust-foundation.gitbook.io/moss-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://hyperdust-foundation.gitbook.io/moss-ai-docs/archived/game/ai-agent-knowledge-management.md).

# AI Agent Knowledge Management

In the MOSS AiPod2, Agent Genetic Module Prompts and RAG Knowledge Bases play distinct roles, each influencing the behavior and information retrieval capabilities of agents.<br>

**Agent Genetic Module Prompts**\
Purpose: Define the agent's persona, language style, and interaction rules, determining how it expresses itself and how it responds to users.\
Trigger: Agent prompts take effect during each inference process, influencing the overall conversational style and behavior of the agent.\
Example: An AI assistant’s prompt might be set to define it as a “witty and humorous financial analyst,” ensuring it maintains a specific tone and professionalism across all conversations.

{% content-ref url="/pages/3MNOnWq7joH25bb971WF" %}
[Edit Agent Gene Module Prompts](/moss-ai-docs/archived/game/ai-agent-knowledge-management/edit-agent-gene-module-prompts.md)
{% endcontent-ref %}

**Agent Knowledge Base**\
Purpose: Stores additional knowledge-based information. When the agent requires specific expertise or content, it retrieves and queries the knowledge base.\
Trigger: The knowledge base is only accessed when the user’s query pertains to related content.\
Example: If the knowledge base contains a "MOSS AI RAG Knowledge Base Creation Guide," the agent will search for and provide that information only when the user asks about it.

{% content-ref url="/pages/h7y1dWtMogLzGFaJ99kG" %}
[Launch RAG Knowledge Base](/moss-ai-docs/archived/game/ai-agent-knowledge-management/launch-rag-knowledge-base.md)
{% endcontent-ref %}


---

# 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://hyperdust-foundation.gitbook.io/moss-ai-docs/archived/game/ai-agent-knowledge-management.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.