> 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/ai/set-up-coupler-io.md).

# Set up Coupler.io

You can create and configure a Coupler.io data flow without leaving your AI tool. Describe the data you want in plain language, and the assistant handles the setup — finding the right integration, configuring the source and destination, and creating the flow for you.

## What you can do with AI

* **Describe what you want in plain language** — for example, "import my HubSpot deals into Google Sheets" or "pull last month's Google Ads campaigns into BigQuery."
* **Set up the source** — the assistant identifies the integration, uses your connected account, and configures what to pull (the entity, date range, filters, and fields).
* **Set up the destination** — choose where the data should go, such as Google Sheets or BigQuery, and configure the target (spreadsheet, table, write mode).
* **Start from a template** — if a pre-built recipe matches your request, use it as a fast starting point instead of configuring everything from scratch.
* **Schedule automatic refreshes** — ask the assistant to run the flow on a schedule (daily, hourly, every 15 minutes, or monthly), and pause or resume it later.
* **Adjust after creating** — ask the assistant to change the source or destination settings on an existing flow.

## Available in

This works in every Coupler.io AI destination: Claude, ChatGPT, Cursor, Custom MCP, Gemini CLI, OpenClaw, and Perplexity.

## Before you start

The assistant sets up flows using the accounts you've **already connected** in Coupler.io — it doesn't create new connections for you. If you haven't connected the source or destination account yet, connect it in Coupler.io first, then ask the assistant to build the flow.

{% hint style="info" %}
If you have more than one connected account for a service, the assistant will ask which one to use.
{% endhint %}

## How it works

{% stepper %}
{% step %}
**Tell the assistant what you want.** State the source, the data you're after, and where it should go — for example, "set up a Stripe invoices export to Google Sheets for the last 30 days." If anything essential is missing, the assistant asks one focused question.
{% endstep %}

{% step %}
**It checks for a template.** If a pre-built template closely matches your request, the assistant offers it as a quick starting point. Otherwise it proceeds with a custom setup.
{% endstep %}

{% step %}
**It configures the source.** The assistant picks the right integration, uses your connected account, and maps your request to the correct entity, date range, filters, and fields.
{% endstep %}

{% step %}
**It configures the destination.** It sets up where the data lands — for example, the target spreadsheet and sheet, or the BigQuery dataset and table.
{% endstep %}

{% step %}
**It confirms and creates the flow.** For a clear request, the assistant creates the flow and reports what it configured. If the request left room for interpretation, it summarizes the setup and asks you to confirm first.
{% endstep %}

{% step %}
**Set a schedule (optional).** Ask the assistant to run the flow automatically — daily, hourly, every 15 minutes, or monthly. It configures the timing for you, so the data refreshes on its own, and you can pause or resume the schedule anytime.
{% endstep %}
{% endstepper %}

## After the flow is created

The assistant won't run the flow automatically — you stay in control. When you're ready, you can:

* Ask the assistant to **run the flow** to fetch the data, then start [analyzing your data](/ai/data-analysis.md).
* Ask the assistant to **change the schedule** — or pause it — whenever your refresh needs change.
* Ask the assistant to **adjust the source or destination** if you want to change what's pulled or where it goes.


---

# 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/ai/set-up-coupler-io.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.