### Answer Yes, you can document your agent's prompt structure. The approach depends on which agent type you're using: For Single/Multi Prompt Agents (with States) : These agents use a tree-like structure with states that can transition between each other [(1) ]() . Each state contains: - A state prompt that defines behavior for that specific stage - State-specific tools that are available in that state - Edges that define transitions to other states The general structure is: System prompt = general prompt + state prompt . You can document this by listing each state name, its prompt, available tools, and transition conditions to other states . For Conversation Flow Agents: These use a node-based structure where each node represents a specific point in the conversation [(2) ]() . You can document: - **Nodes**: Different types including conversation nodes, function nodes, logic nodes, and end nodes - **Edges**: Connections between nodes that define transition logic, including condition-based transitions and dynamic routing - **Global Settings**: Configuration that applies to the entire conversation including global prompt, voice, and language settings Both approaches allow you to create structured documentation of your agent's conversational logic and flow.

​ To learn more, see the sources I considered: [[1] Create Retell LLM](https://docs.retellai.com/api-references/create-retell-llm) [[2] Conversation Flow Overview](https://docs.retellai.com/build/conversation-flow/overview) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.