The Retell Community is where innovators, call center leaders, and AI enthusiasts come together to share ideas, learn best practices, and explore the future of voice automation. Join to connect with peers, get early access to product updates, and collaborate on building human-like AI voice experiences that transform customer service.

Retell AI

<@1145576664366055464> Why does the agent say outloud the internal thinking and tool usage? Is there a way to prevent this?

Thanks for tagging me <@550841198168899616>. I'll look through relevant sources and get back to you shortly.

### Answer
 This is a known issue where agents sometimes verbalize tool calls, transitions, or internal logic out loud (e.g., saying "transitioning to close the conversation" or "end underscore call") . [(1) ](<https://discord.com/channels/1186424376300679209/1261332783993982986>)

**How to address it:**

The primary solution is **better prompting**. You should:

1. **Explicitly instruct the agent** in your prompt to never speak tool names, function calls, or transition states out loud
2. **Use a more capable model** — using a better LLM tends to generate better responses and reduces this behavior 

For example, add clear instructions like:
- "Never say tool names, function names, or internal states out loud"
- "Do not verbalize any technical operations or transitions"

This behavior is generally a prompting issue rather than a platform limitation.

​
To learn more, see the sources I considered:

[[1] The agent sometimes says tool calls and transitions out loud](https://discord.com/channels/1186424376300679209/1261332783993982986)
​

Feel free to tag <@1145576664366055464> with additional questions. I also appreciate feedback, it helps me improve.