### Answer For Conversation Flow agents, the transition timing behavior depends on how you configure the Function Node settings: When transitions happen based on user interruption: - If the user interrupts the agent, the transition can happen once the user is done speaking [(1) ]() - If

wait for result

is turned on and the user interrupts, the transition happens once the function result is ready and the user is done speaking Key settings to control this behavior: - **Wait for Result**: When enabled, the agent will wait for the function to finish executing before attempting to transition to any other node - **Block Interruptions**: When enabled, the agent will not be interrupted by the user when speaking So if you want to ensure the agent waits until the user finishes speaking before executing transitions: 1. The turn-taking model already accounts for when the user is done speaking before allowing transitions 2. You can enable Block Interruptions on specific nodes if you want the agent to complete its speech without user interruption 3. Enable Wait for Result if you need function results to be ready before transitioning For Agent Transfer specifically, you can configure "Speak during execution and messages" to control whether the agent says something while performing the transfer [(2) ]() [(3) ]()

​ To learn more, see the sources I considered: [[1] Function Node Overview](https://docs.retellai.com/build/conversation-flow/function-node) [[2] Agent Transfer](https://docs.retellai.com/build/single-multi-prompt/transfer-agent) [[3] Agent Transfer Node](https://docs.retellai.com/build/conversation-flow/transfer-agent-node) ​

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

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] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) ​

### Answer For Conversation Nodes, transitions happen when the user is done speaking. [(1) ]() Key settings to control this behavior: - **Block Interruptions**: When enabled, the agent will not be interrupted by the user when speaking. - **Skip Response**: When enabled, the transition will only have one edge, and when the agent is done talking, it will transition to the next node via that specific edge (useful for disclaimers where you don't need a user response to move on) . So by default, Conversation Nodes already wait for the user to finish speaking before evaluating transition conditions. If you want to ensure the agent completes its speech without any user interruption, enable Block Interruptions on that node.