### Answer Finetune examples are specifically designed for Conversation Flow agents, not single/multi prompt agents. [(1) ]() In Conversation Flow, finetune examples help improve agent response or transition behavior when it's not meeting your expectations. They're supported in these nodes: - **Conversation Node**: supports finetune examples for response and transition - **Subagent Node**: supports finetune examples for response and transition - **Function Node**: supports finetune examples for transition When configuring finetune examples, you provide a transcript as context with roles like

user

,

agent

, or

function

. For the

function

role, you can fill out both the invocation and result. **For conversation finetuning**: You only need to supply the relevant transcript portion as context, with at least one

agent

response required. **For transition finetuning**: You need both a transcript as context and the transition result. For single/multi prompt agents, the documentation doesn't mention finetune examples as a feature. Instead, these agents rely on prompt engineering techniques like sectional prompts and explicit tool calling instructions. [(2) ]()

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

​ To learn more, see the sources I considered: [[1] Finetune Examples](https://docs.retellai.com/build/conversation-flow/finetune-examples) [[2] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) ​

### Answer To create nodes for sending SMS messages when callers request specific information like pricing or documentation, you can use a Subagent Node with the Send SMS tool attached. [(1) ]() Here's how to structure it: Node Setup: 1. Create a Subagent Node that handles the conversation about pricing/documentation 2. In the node instruction, write a prompt like:

When the user asks about pricing or documentation, offer to send them a link via SMS. 
Ask for confirmation before sending. If they agree, use the SMS tool to send the 
appropriate link based on their request.

3. Add the Send SMS tool to this subagent node How It Works: Subagent nodes allow the LLM to decide when to call tools based on conversation context. The agent will: - Detect when the user asks about pricing/documentation - Offer to send the link via SMS - Wait for user confirmation - Call the SMS tool only when the user agrees Key Points: - The Send SMS tool is available as one of the tool types you can attach to subagent nodes - Multiple tools can be added to a single subagent node - The agent can continue talking while a tool executes - Tool results are available to the LLM for generating follow-up responses This approach gives you context-dependent SMS sending where the agent naturally asks for permission before sending, rather than automatically firing the SMS on every mention of pricing or documentation.

​ To learn more, see the sources I considered: [[1] Subagent Node](https://docs.retellai.com/build/conversation-flow/subagent-node) ​

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