> ## Documentation Index
> Fetch the complete documentation index at: https://docs-dev.setoo.work/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM Tab

> Model, temperature, and max tokens

| Field               | Description                     | Default   |
| ------------------- | ------------------------------- | --------- |
| Model               | Which LLM to use for this agent | —         |
| Temperature         | Randomness of responses (0–1)   | Low       |
| Max Response Length | Caps how long a response can be | Short     |
| Response Mode       | Streaming or batch delivery     | Streaming |

<Callout type="tip">
  A lower temperature keeps responses consistent for support agents. Higher
  values suit creative or sales-oriented agents.
</Callout>