> For the complete documentation index, see [llms.txt](https://docs.aisera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisera.com/aisera-platform/ai-automation-optimize-flow/ai-workflow-studio/building-workflows/use-a-workflow-as-an-nlu-pipeline.md).

# Use a Workflow as an NLU Pipeline

You can now define and select a **Workflow** as a **Fulfillment** pipeline and add it as a segment anywhere within the existing pipeline. The **Workflow** can fulfill the user’s **Request** or pass the question on to the next pipeline.

#### To Set Up Workflow as an NLU Pipeline: <a href="#to-set-up-workflow-as-an-nlu-pipeline" id="to-set-up-workflow-as-an-nlu-pipeline"></a>

1. Use the **Workflow Studio** to create a **Workflow** to serve the **Request**, with the parameters shown in the diagram below.

<div align="left"><figure><img src="/files/hqrvTHfDIW0dapPVKReB" alt="" width="563"><figcaption></figcaption></figure></div>

2\. Open the **Advanced** settings window for a new or existing application/bot.

3\. Select **Workflow** in the **Fulfillment Engines** field.

<div align="left"><figure><img src="/files/bFaXHStH1zwLU0qSqheB" alt="" width="563"><figcaption></figcaption></figure></div>

4\. In the **Flow** field, select the flow you want to use from the pull-down list.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://docs.aisera.com/aisera-platform/ai-automation-optimize-flow/ai-workflow-studio/building-workflows/use-a-workflow-as-an-nlu-pipeline.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.