> ## Documentation Index
> Fetch the complete documentation index at: https://ai-kb.automationanywhere.com/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM

> Send a prompt to a language model and return the generated response.

The **LLM** node sends a prompt to a language model and returns the generated text. Use it to summarize content, classify data, transform text, answer questions, or perform any task that benefits from AI-generated output.

## Configuration

| Field             | Required | Description                                                                                                                       |
| ----------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------- |
| **Prompt**        | Yes      | The prompt to send to the language model. Type `@` to insert variables from previous steps.                                       |
| **Model**         | No       | The language model to use for processing. Select from the dropdown.                                                               |
| **System Prompt** | No       | System-level instructions that define the model's behavior and role. Type `@` to insert variables or enter instructions directly. |
| **Temperature**   | No       | Controls the randomness of the output. `0` = deterministic, `1` = very random. Default is `0.7`.                                  |
| **Max Tokens**    | No       | The maximum number of tokens in the response. Range is 1–32000. Default is `1000`.                                                |

## Results

The **Results** tab shows the model's generated response after the node is executed.

<AccordionGroup>
  <Accordion title="Notes">
    * Use the **System Prompt** to set a persona or constrain the model's behavior (e.g. "You are a helpful assistant that only answers questions about finance.").
    * Lower **Temperature** values produce more consistent, focused outputs. Higher values produce more creative or varied responses.
    * Increase **Max Tokens** for longer outputs, or decrease it to limit response length and reduce token usage.
  </Accordion>
</AccordionGroup>