### Answer To reduce your agent from interrupting users, you can adjust these agent settings: 1. Lower the

responsiveness

value This controls how responsive the agent is. Value ranges from [0,1]. Lower value means less responsive agent (wait more, respond slower) , while higher value means faster exchanges (respond when it can) . [(1) ]() 2. Increase the

interruption_sensitivity

value This controls how sensitive the agent is to user interruptions. Value ranges from [0,1]. Lower value means it will take longer/more words for user to interrupt agent, while higher value means it's easier for user to interrupt agent. When set to 0, the agent would never be interrupted. You can update these via the API:

javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const agentResponse = await client.agent.update('16b980523634a6dc504898cda492e939', { agent_name: 'Jarvis' }) ;
console.log(agentResponse.agent_id) ;

[(2) ]() You can also dynamically update these settings mid-call via the LLM WebSocket using an

update_agent

event with

responsiveness

and

interruption_sensitivity

in the

agent_config

object. [(3) ]() **Prompt-based approach**: Some community members have had success adding interruption handling instructions to their prompts—having the agent pause and ask "Did you say something?" when it detects noise, then resuming appropriately based on the user's response. [(4) ]() [(8) ]()

​ To learn more, see the sources I considered: [[1] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[3] LLM WebSocket](https://docs.retellai.com/api-references/llm-websocket) [[4] Discord message from @bajacheebo on 2025-01-07](https://discord.com/channels/1186424376300679209/1294891368505937952/1325992277759365161) ​

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