### Answer I don't have specific information in the available sources about configuring how agents acknowledge interruptions in Conversation Flow nodes. The documentation covers the Block Interruptions setting, which when enabled prevents the agent from being interrupted while speaking [(1) ]() [(2) ]() , but doesn't detail customizing the agent's response behavior after an interruption occurs. For configuring more natural interruption handling with acknowledgment phrases like "oh, oops, what I was trying to say was," you might need to: - Adjust your node instruction prompts to include guidance on how to handle interruptions - Use the Fine-tuning Examples feature available in both Conversation and Subagent nodes to train the agent on preferred interruption responses Retell AI's turn-taking model handles interruptions through advanced contextual understanding and predictive timing [(3) ]() , but the specific customization of post-interruption acknowledgment behavior isn't documented in the available sources. For more detailed guidance on this specific use case, I'd recommend: - [Conversation Node]() - [Subagent Node]() Would you like a general answer based on my knowledge instead?

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] Subagent Node](https://docs.retellai.com/build/conversation-flow/subagent-node) [[2] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) [[3] Retell AI's Turn-Taking Model for Seamless Calls | Retell AI](https://www.retellai.com/blog/how-retell-ais-turn-taking-model-ensures-seamless-calls) ​