### Answer This behavior is likely related to the "Speak After Execution" setting in your custom function configuration. [(1) ]() When a tool call completes but the agent doesn't wait or acknowledge the response before transitioning, the most common cause is that "Speak After Execution" is not enabled. This setting controls whether the agent speaks after the function completes—without it, the agent may immediately proceed to the next node without verbally processing the tool result. To fix this: 1. Go to your custom function configuration in the Conversation Flow 2. Enable "Speak After Execution" This ensures the agent will speak based on the function result before moving on. Additional considerations: - If your function is configured as "Optional" in the node, the LLM decides whether to call it based on context—it may skip it entirely in some cases [(2) ]() - Verify your "Speak During Execution" and "Speak After Execution" settings are properly configured for your use case - There have been reported issues where conversation flow function nodes behave differently on telephony/voice calls versus text chat testing [(3) ]() [(4) ]() If you're still experiencing issues after enabling "Speak After Execution," check your call detail logs for any errors related to tool call responses. [(4) ]()

​ To learn more, see the sources I considered: [[1] Tool calling - AI agent doesn't reply back. Stops interacting](https://community.retellai.com/t/tool-calling-ai-agent-doesnt-reply-back-stops-interacting/327) [[2] Custom Function](https://docs.retellai.com/build/conversation-flow/custom-function) [[3] Discord message from @momsramen on 2025-07-22](https://discord.com/channels/1186424376300679209/1186462578310910112/1397031478965043312) [[4] Conversation flow agent stops speaking after calling function](https://discord.com/channels/1186424376300679209/1394277381782638672) ​

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

### Answer Since "Speak After Execution" is already enabled, here are other settings and factors to check: 1. Enable "Wait for Result" In your Function Node settings, ensure "Wait for Result" is turned on. [(1) ]() When enabled, the agent will wait for the function to finish executing before attempting to transition to any other node—this guarantees that when you reach the next node, the result is already ready to be used. 2. Check Transition Timing Logic The transition behavior depends on the combination of settings: - If

wait for result

is turned off, the agent transitions immediately after the function gets invoked (or once done talking if "Speak During Execution" is on) - If

wait for result

is turned on, the agent transitions once the function result is ready and the agent is done talking 3. Separate Functions into Different States If you have multiple tools available in the same state, the LLM might prioritize one over another. Consider creating a dedicated state/node for your function that transitions to the next node only after completion. [(2) ]() 4. Verify Your Transition Conditions Since the function node takes function results into consideration for transition timing, you can write your transition condition to be based on the function result. [(1) ]() If "Wait for Result" is already enabled and you're still experiencing this issue, this may require further investigation from the Retell team.

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] Function Node Overview](https://docs.retellai.com/build/conversation-flow/function-node) [[2] Custom function not executing despite being configured as tool in state](https://community.retellai.com/t/custom-function-not-executing-despite-being-configured-as-tool-in-state/705) ​