### Answer Yes, you can influence how your agent handles interruptions through a few approaches: ## Using Custom LLM WebSocket If you're using a Custom LLM, you receive

turntaking

events that indicate when the speaker changes. [(1) ]() The

turntaking

field will be present when the speaker changes to user (

user_turn

) or right before the agent is about to speak (

agent_turn

) . This allows you to track when an interruption occurred and craft a contextually appropriate response rather than simply repeating. ## Adjusting Agent Settings You can configure these parameters via the Update Voice Agent API to affect interruption behavior: [(2) ]() - **`responsiveness`**: Controls how responsive the agent is (0-1) . Lower values make the agent wait more before responding. - **`interruption_sensitivity`**: Controls how sensitive the agent is to user interruptions (0-1) . Lower values mean it takes longer for the user to interrupt. ## Prompt Engineering The most effective way to control post-interruption behavior is through your agent's prompt. You can instruct the LLM to acknowledge interruptions naturally (e.g., "Sure, go ahead" or "Of course, what would you like to ask?") rather than repeating the interrupted content. ## Turn-Taking Model Retell AI's proprietary turn-taking model uses predictive timing to ensure smooth transitions between speakers and learns from interactions to adapt to different conversational styles. [(3) ]() For more granular control over post-interruption responses, using a Custom LLM gives you the most flexibility since you can detect the interruption via the

turntaking

event and respond accordingly. [(1) ](https:/

/docs.retellai.com/api-references/llm-websocket)

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] LLM WebSocket](https://docs.retellai.com/api-references/llm-websocket) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[3] Performance-related configurations and noticeable latency during live calls](https://community.retellai.com/t/performance-related-configurations-and-noticeable-latency-during-live-calls/747) ​