# Generative AI

One of the unique abilities of our product is the ablility to create runnable workflows from natural language. 

1. Select a flow from the sidebar or create a new flow.
2. Click `Generate` from the top right corner of the header.
3. This will show a popup box asking for the model\_name and description of your flow in natural language.

<figure><img src="/files/AZw1H5KhCqUhyBkEQUC0" alt="" width="375"><figcaption></figcaption></figure>

4. Currently we only support OpenAI, but we plan to integrate other models soon. Let us know if you want a specific model integrated.
5. Request your OpenAI api key by signing up [here](https://platform.openai.com/) or you can contact us on our [social media handles](https://flowtestai.gitbook.io/flowtestai) and we can provide you one based on your use case.
6. Now head to the directory where you created your collection in your file system. Create a `.env` file and enter `OPENAI_APIKEY=<api_key_value>` . Once you do that you should start seeing that in the `Generate` pop up box if you select OPENAI as your choice of model.

<figure><img src="/files/Een1Tp7gtSIG2ypPO3Ip" alt="" width="375"><figcaption></figcaption></figure>

6. Now that you have everything set, describe your flow, click `Generate` and you will soon see a series of nodes connected together to form a workflow. You can run the workflow, modify it by adding more logical nodes and finally save it for future use.


---

# 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://flowtestai.gitbook.io/flowtestai/generative-ai.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.