> For the complete documentation index, see [llms.txt](https://docs.coupler.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.coupler.io/destinations/categories/ai/chatgpt.md).

# ChatGPT

ChatGPT is an AI assistant from OpenAI that lets you explore, analyze, and ask questions about your data in plain language. By connecting Coupler.io to ChatGPT, you can pull business data from any of your sources — CRMs, e-commerce platforms, databases, and more — and interact with it conversationally, no SQL or coding required.

## Why use ChatGPT as a Coupler.io destination?

* **Natural language analysis** — Ask questions like "What were my top 5 products last month?" or "Which deals are stalled in my pipeline?" without writing a single formula.
* **Any source, one interface** — Send data from HubSpot, Shopify, Google Analytics, or any other Coupler.io source directly into ChatGPT for unified analysis.
* **No export/import friction** — Your data flows directly into a custom GPT, so you're always working with fresh data rather than stale spreadsheet exports.
* **Accessible to non-technical users** — Anyone on your team can explore data through conversation, not dashboards or query editors.

## Prerequisites

* A **ChatGPT account**

## Quick start

{% hint style="success" %}
Set up your data flow in Coupler.io first, run it successfully, and then install and open the Coupler.io ChatHPT app to start asking questions about your data.
{% endhint %}

## How to connect

{% stepper %}
{% step %}
**Create a new data flow and add a source.** In Coupler.io, create a new data flow and connect the data source you want to analyze — for example, HubSpot deals, Shopify orders, or any other supported source. Configure what data you want to pull.
{% endstep %}

{% step %}
**Select ChatGPT as your destination.** In the destination step of your data flow, choose **ChatGPT** from the list of available destinations.
{% endstep %}

{% step %}
**Connect to Coupler.io ChatGPT app.** Install the [Coupler.io ChatGPT app](https://l.rw.rw/couplerio-chatgpt-app) and pass the authentication.
{% endstep %}

{% step %}
**Run your data flow.** Click **Run** to execute the data flow manually. This pushes your data to Coupler.io and makes it available for the ChatGPT integration. Wait for the run to complete successfully before moving on.
{% endstep %}

{% step %}
**Install ChatGPT app.** Navigate to the apps section in ChatGPT settings using the link provided in your Coupler.io account. Install the app and authorize when prompted.
{% endstep %}

{% step %}
**Start analyzing your data.** Ask questions about your dataset in plain English. ChatGPT will query your connected data and return answers, summaries, and insights — all within the conversation.
{% endstep %}
{% endstepper %}

## Supported features

| Feature              | Supported |
| -------------------- | --------- |
| Replace mode         | Yes       |
| Append mode          | No        |
| Automatic scheduling | Yes       |
| Type enforcement     | No        |
| Templates            | No        |


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.coupler.io/destinations/categories/ai/chatgpt.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.