> 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/perplexity.md).

# Perplexity

Perplexity is an AI-powered answer engine that lets you have conversational, research-style interactions with your data. By connecting Coupler.io to Perplexity, you can bring live business data directly into your Perplexity sessions and ask questions in plain language — no SQL, no pivot tables.

## Why use Perplexity as a destination?

* **Ask questions about your data conversationally** — query marketing metrics, sales numbers, or operational data the same way you'd ask a colleague
* **Combine data from any source** — Coupler.io supports dozens of sources, so you can pull from CRMs, ad platforms, spreadsheets, and databases all into one Perplexity-ready dataset
* **No technical setup on the data side** — Coupler.io handles the extraction, transformation, and delivery so you can focus on the analysis
* **Always up to date** — schedule your data flow to refresh automatically and your Perplexity context stays current

## Prerequisites

* A Perplexity account

## Quick start

{% hint style="success" %}
Before you begin, make sure you know which data you want to analyze — having a clear question in mind (e.g., "What were my top-performing ad campaigns last month?") will help you choose the right source and configure your data flow effectively.
{% endhint %}

## How to connect

{% stepper %}
{% step %}
**Create a new data flow and add a source.** In Coupler.io, click **Add data flow** and choose the source application you want to pull data from — for example, Google Analytics, HubSpot, or Airtable.
{% endstep %}

{% step %}
**Select Perplexity as your destination.** In the destination step, search for and select **Perplexity** from the list of available destinations.
{% endstep %}

{% step %}
**Make sure Docker is installed and running.** Currently, Perplexity uses local MCP instead of the remote one, so it needs Docker to connect.
{% endstep %}

{% step %}
**Add Coupler.io connector**. Navigate to Settings -> Connectors, click "Add new connector" and proceed with the Simpler settings.
{% endstep %}

{% step %}
**Create new connection**. Call it "coupler-io" and pass the following command: `docker run --pull=always -e COUPLER_ACCESS_TOKEN --rm -i ghcr.io/railsware/coupler-io-mcp-server`
{% endstep %}

{% step %}
**Paste your access token**. Create an environmental variable called `COUPLER_ACCESS_TOKEN` , then generate and paste your personal access token
{% endstep %}

{% step %}
**Save your configuration**. Agree with the security warning aboit Docker
{% endstep %}

{% step %}
**Run your data flow.** Click **Run** to execute your first manual sync. Once the run completes successfully, your data will be available in Perplexity, and you can start asking questions about it.
{% 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/perplexity.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.