# Actions

Actions are core components of the application. Actions uses large language model that takes data from input elements, knowledge base and agents as inputs and returns messages as outputs based on the prompt. You can specify system instructions, prompts, interchange between different providers and models. Each action step can either be final output or intermediate depending one the use case.

<figure><img src="/files/rCSVWCbIazoiY2uVbwn7" alt=""><figcaption></figcaption></figure>

### Text to Text

Creates text from text input. You need to specify the task in the prompt box. You can use the input variables as well as result generated from previous steps as input to prompt.&#x20;

<figure><img src="/files/wZrnZ0LPEyhaKdZYWI7d" alt=""><figcaption></figcaption></figure>

Model Setting - In the model setting tab, you can switch between different LLM providers, models, temperature and maximum output length.

<figure><img src="/files/IDgqgX1invCPbIcoBaCh" alt=""><figcaption></figcaption></figure>

### Summarizer

Summarizer action can be used to review a document and generate a summary of the content.

<figure><img src="/files/CV6045rdckj3pgdrmv52" alt=""><figcaption></figcaption></figure>

*Currently, summarizer only works with UI Data Loaders.*


---

# 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://document.unifiedstacks.com/workflow-elements/actions.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.