### Answer Yes, you should use an Extract Dynamic Variable node after the agent speaks to capture the user's selection. [(1) ]() Here's how to set it up: 1. Add an Extract Dynamic Variable node following the conversation node where the agent presents the options 2. Configure the variable by filling in: - **Variable Name**: A short name to reference this variable (e.g.,

selected_time

) - **Description**: Brief explanation of what this value should be (e.g., "The time slot selected by the user") - **Variable Type**: Choose the appropriate type - likely Text for "9am" or Enum if you have predefined options 3. For Enum type, you can specify the exact options (9am, 10am, etc.) to help the LLM extract accurately 4. **Access in Code Node**: Once extracted, you can use the variable in your Code Node by referencing it as

dv.selected_time

(or whatever you named it) [(2) ]() The Extract Dynamic Variable node is specifically designed to pull information from the conversation and store it as a dynamic variable [(1) ]() - this is the recommended approach for capturing user selections. **Important**: When using the extracted variable in your Code Node, reference it directly by name like

{{selected_time}}

, not with prefixes like

node_name.selected_time

[(3) ]()

​ To learn more, see the sources I considered: [[1] Extract Dynamic Variable Node](https://docs.retellai.com/build/conversation-flow/extract-dv-node) [[2] Code Node](https://docs.retellai.com/build/conversation-flow/code-node) [[3] Extracted Dynamic Variables not sending through custom function in Conversation Flow Prompt](https://discord.com/channels/1186424376300679209/1442542149546803312) ​

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