> 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 %}