​ To learn more, see the sources I considered: [[1] Extract Dynamic Variables](https://docs.retellai.com/build/single-multi-prompt/extract-dv) ​

### Answer --- I don't have specific information in the available sources about whether Retell AI forces the agent to speak immediately after an Extract Dynamic Variable tool call. The documentation for the Extract Dynamic Variable tool covers how to add the tool, define variables, and update your prompt to specify when to invoke it [(1) ]() , but it doesn't explicitly describe the agent's speaking behavior after the tool executes. Check out these potentially useful sources: - [Extract Dynamic Variables]() - [Dynamic Variables]() Would you like me to try to answer generally based on my knowledge instead?

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

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

### Answer --- Yes, there have been reports, though the issue described is actually the *opposite*—agents stopping speaking after tool calls rather than speaking unintentionally. A recent incident (July 2025) affected Conversation Flow agents where, after successfully calling a function, the AI would stop talking even though logs showed correct node transitions. [(1) ]() The error in logs was: > "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'." This was a platform-level issue that was resolved by the Retell team. If you're experiencing agents speaking when they shouldn't after tool calls, that's typically a prompt engineering issue. You can address this by providing explicit tool calling instructions that define: - When to call tools (trigger words/conditions) - What to do after retrieving information [(2) ]() For example, you can specify post-tool behavior like: > "After retrieving information: Always summarize what you found, then ask if they need additional help." If your agent is speaking unexpectedly after tool calls, consider adding clearer boundaries in your prompt about when the agent should remain silent or wait. ---

​ To learn more, see the sources I considered: [[1] Conversation flow agent stops speaking after calling function](https://discord.com/channels/1186424376300679209/1394277381782638672) [[2] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) ​