# LLM Processing

The LLM Processing action sends a prompt to a configured LLM at any point in the chat flow, returning the result for use in downstream actions.

***

Select an LLM Processing action from the tree to open its settings:

* **Input** – the text prompt sent to the LLM. Supports chat variables.
* **Script** – toggle to supply the input as a chat script expression instead.
* **Model** – the LLM to use: DeepSeek V2 , GPT-4o , Qwen 2.5 , Llama 3.2
* **Temperature** – controls response randomness. Range: 0.0–2.0. Default: 1.
* **System Prompt** – prompt template used to provide instructions or context to the LLM when generating responses.
* **Script** – toggle to supply the system prompt as a chat script expression instead.
* Use **Knowledge** info to provide more context – toggles whether the LLM can access training sources from the LLM tab.
* **Resulting variable** – the name of the chat variable that will store the LLM’s response.

Press **Save** to confirm edits.

***

#### Outcome branches

The action branches into Success, Error, and Timeout outcomes. Nest subsequent actions under each branch as needed.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://documentation.proto.cx/docs/modules/ai-agents/workflows-and-actions/llm-processing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.