# Using ChatGPT To Create Zaps

Zapier offers a ChatGPT plugin that simplifies the process of creating zaps. With the power of natural language processing, you can draft zaps effortlessly within ChatGPT. Below is a step-by-step guide to get started.

***

**Prerequisites:**

* **ChatGPTPlus**: You need a [ChatGPT](https://chat.openai.com/auth/login)[ account](https://chat.openai.com/auth/login) and a Plus subscription to access plugins. If you're not already subscribed, you can upgrade via the ChatGPT menu in the bottom left of their interface.
* **Zapier Account:** You need a Zapier account - if you don't have one, you can [sign up here](https://zapier.com/sign-up).

***

**Setup Directions:**

1. Once inside ChatGPT, initiate a new chat. Click on the **latest available GPT version** at the top of the interface.
2. From the dropdown that appears, select the **Plugins**.
3. A new dropdown will appear showcasing available plugins and the option to visit the plugin store. Go to the **plugin store**.
4. In the plugin store, search for "Zapier". Once found, connect the Zapier plugin to your ChatGPT account.
5. Back in the chat, select the Zapier plugin. Describe the automation you wish to create in natural language.
6. ChatGPT, with the help of the Zapier plugin, will provide a link containing a draft for your desired automation. Click on this link to open it in Zapier. From there, you can tailor the draft to your specific needs and, once satisfied, publish it live.

With these steps, you can harness the combined power of ChatGPT and Zapier to create efficient and tailored automations for your needs. Happy zapping!


---

# 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://docs.whiteswan.io/partner-knowledge-base/zapier-integration/using-chatgpt-to-create-zaps.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.