> 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

Connect your business data to Perplexity AI via Coupler.io for conversational data analysis without SQL or pivot tables.

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        |

## Perplexity common issues

### Connection issues

<details>

<summary>My Perplexity account isn't connecting or authorizing correctly</summary>

This can happen if the Coupler.io connector or extension hasn't been properly installed in Perplexity. Go back through the connection step and make sure you've completed any in-app authorization steps on the Perplexity side — not just the Coupler.io side.

Try disconnecting and reconnecting your Perplexity account from within the data flow settings. If the issue persists, check whether your Perplexity plan supports third-party connectors.

</details>

### Data issues

<details>

<summary>Perplexity doesn't seem to "see" my data after a successful run</summary>

After a successful Coupler.io run, it may take a short moment for the data to become fully available in your Perplexity session. Try refreshing your Perplexity session or starting a new conversation.

Also, confirm that the dataset name you configured in Coupler.io matches what you're referencing when querying in Perplexity. A naming mismatch can make data hard to locate.

</details>

<details>

<summary>My dataset in Perplexity contains fewer rows than expected</summary>

Check whether your source is applying filters that limit the returned rows. Some sources have default date range filters or row caps. Review your source configuration in Coupler.io and expand the date range or increase the row limit if needed.

</details>

### Permission errors

<details>

<summary>I get a permissions error when trying to save or run the data flow</summary>

Make sure your Coupler.io account has the necessary permissions to create and run data flows. If you're on a team account, your role may restrict which destinations you can configure — ask your workspace admin to verify your permissions.

</details>

## Perplexity FAQ

<details>

<summary>What data sources can I send to Perplexity through Coupler.io?</summary>

Any source supported by Coupler.io can be sent to Perplexity. This includes CRMs like HubSpot and Salesforce, ad platforms like Google Ads and Meta Ads, project management tools like Asana and Jira, spreadsheets, databases, and many more. You're not limited to a single source — a single data flow can combine multiple sources using Join or Append transformations before delivering to Perplexity.

</details>

<details>

<summary>Do I need to know how to code or write queries to use Coupler.io with Perplexity?</summary>

No coding is required. Coupler.io handles the data extraction and delivery through a visual interface, and Perplexity lets you interact with that data using plain language questions. The combination is designed to make data analysis accessible without any technical background.

</details>

<details>

<summary>How often will my data in Perplexity be updated?</summary>

Once your data flow has completed a successful manual run, you can set up automatic scheduling in Coupler.io. You can choose how frequently the data refreshes — hourly, daily, weekly, or on a custom interval. Each scheduled run will update the dataset in Perplexity according to the write mode you selected.

Every time you start a new chat, Perplexity collects fresh data. If you want it to fetch updated data in the ongoing conversation, ask it to do so directly.

</details>

<details>

<summary>Can I send data from multiple sources into a single Perplexity dataset?</summary>

Yes. Coupler.io supports multiple sources within a single data flow. You can use the **Join** transformation to merge related datasets (e.g., combining CRM deals with ad spend data) or **the Append** transformation to stack data from different sources into a single unified table before sending it to Perplexity.

</details>

<details>

<summary>What kinds of questions can I ask Perplexity about my data?</summary>

Perplexity works best with clear, specific questions tied to the data you've loaded. Good examples include:

* "Which product category had the highest revenue last quarter?"
* "Show me the trend in customer acquisition cost over the past 6 months."
* "Which sales rep closed the most deals in the dataset?"

The more focused your question, the more useful Perplexity's response will be.

</details>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

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

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
