Set up Coupler.io

You can create and configure a Coupler.io data flow through conversation — with the Coupler.io AI Agent inside the app, or straight from an external AI tool you've connected as a destination (Claude, ChatGPT, and more). 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 the Coupler.io AI Agent and every 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.

If you have more than one connected account for a service, the assistant will ask which one to use.

How it works

1

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.

2

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.

3

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.

4

It configures the destination. It sets up where the data lands — for example, the target spreadsheet and sheet, or the BigQuery dataset and table.

5

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.

6

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.

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.
• 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.