### Answer Based on the available documentation, the behavior of

speak_after_execution

when a custom function returns an HTTP 500 status is not explicitly documented [(1) ]() . The documentation specifies that for custom functions, the response should have a status code between 200-299 to indicate success of the HTTP request . When a request fails, it will be retried up to 2 times . However, the documentation does not explicitly state whether

speak_after_execution

still triggers after a 500 error or how the agent behaves in this failure scenario. For general function execution behavior,

speak_after_execution

determines whether the agent would keep talking or perform other actions after the function call is completed . The documentation notes that both Speak During Execution and Speak After Execution are

Prompt

based, meaning the LLM will generate the message based on the configuration and the conversation . I don't have specific information about the agent's behavior when

speak_after_execution

is enabled but the function returns a 500 error. You might want to test this scenario or reach out to support for clarification on error handling behavior.

​ To learn more, see the sources I considered: [[1] Integrate any system with custom function](https://docs.retellai.com/build/single-multi-prompt/custom-function) ​

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