***

title: set_internal_fillers
slug: /reference/python/agents/agent-base/set-internal-fillers
description: Set filler phrases for native SWAIG functions.
max-toc-depth: 3
---------------------

For a complete index of all SignalWire documentation pages, fetch https://signalwire.com/docs/llms.txt

[ref-agentbase]: /docs/server-sdks/reference/python/agents/agent-base

Set filler phrases for native SWAIG functions. Internal fillers are phrases the AI
speaks while executing built-in functions like `check_time`, `next_step`, or
`wait_for_user`. They prevent silence during processing and make the conversation
feel more natural.

## **Parameters**

<ParamField path="internal_fillers" type="dict[str, dict[str, list[str]]]" required={true} toc={true}>
  Nested dictionary mapping function names to language-specific filler phrases.
  Format: `{"function_name": {"language_code": ["phrase1", "phrase2"]}}`.
</ParamField>

## **Returns**

[`AgentBase`][ref-agentbase] -- Returns self for method chaining.

## **Example**

```python {5}
from signalwire import AgentBase

agent = AgentBase(name="support", route="/support")
agent.set_prompt_text("You are a helpful assistant.")
agent.set_internal_fillers({
    "next_step": {
        "en-US": ["Moving on...", "Great, let's continue..."],
        "es": ["Pasando al siguiente paso...", "Continuemos..."]
    },
    "check_time": {
        "en-US": ["Let me check the time...", "One moment..."]
    }
})
agent.serve()
```