> For the complete documentation index, see [llms.txt](https://docs.frase.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.frase.io/automations/meet-the-frase-agent.md).

# Meet the Frase Agent

Your built-in operational AI SEO and GEO assistant that understands your site, content, and goals — and can execute workflows on your behalf from a single conversation.

{% embed url="<https://youtu.be/fYEwELG-fWU>" %}

{% hint style="info" %}
**Want Frase inside your own tools?** The same agent that runs here also works through MCP — connect Frase to Claude, Cursor, or any MCP client and run research, briefs, audits, and publishing by just asking. See [**Automate with Claude & MCP.**](/automations/automate-with-frase-mcp.md)
{% endhint %}

## How It Works

### What the Agent Can Help You Do

In one conversation, the Frase Agent can:

* **Research and plan:** Analyze and research keywords, competitors, and content gaps to find opportunities worth pursuing.\ <i class="fa-hand-point-right" style="color:$primary;">:hand-point-right:</i> “Research content gaps in the CRM software space.”
* **Create new content:** Generate briefs, full articles, and content optimized for both search engines and AI platforms.\ <i class="fa-hand-point-right" style="color:$primary;">:hand-point-right:</i> “Create a brief and write a comparison article for HubSpot vs Salesforce.”
* **Improve what already exists:** Identify specific SEO and GEO improvements and apply them automatically.\ <i class="fa-hand-point-right" style="color:$primary;">:hand-point-right:</i> “Optimize this article for GEO and improve its SEO score.”
* **Understand your site:** Run audits, detect keyword cannibalization, track AI visibility, and monitor performance.\ <i class="fa-hand-point-right" style="color:$primary;">:hand-point-right:</i> “Run a site audit and show me pages competing for the same keywords.”
* **Publish content:** Launch blog posts directly to your CMS, create topic clusters, and repurpose content across social and email channels.\ <i class="fa-hand-point-right" style="color:$primary;">:hand-point-right:</i> “Publish this article to WordPress as a draft and create a LinkedIn carousel.”

{% hint style="success" %}
**And if you’re still learning Frase?** The Agent can explain how features work and how to use the platform more effectively. It can even help you navigate the page you're on in the UI.
{% endhint %}

### What the Agent Knows

The Agent has access to your:

* Site data
* Brand Hub settings
* Content library
* Performance data

This is what makes its recommendations specific to **you**. The more you've set up in Frase — your brand profile, integrations, content history — the more useful the Agent becomes.

{% hint style="warning" %}
The Agent **does not** have the ability to access pricing or your plan or billing information. If you need further assistance, reach out to [**support@frase.io**](mailto:support@frase.io).
{% endhint %}

## Best Practices

A few tips to success when using the Agent:

* **Start with a clear goal, not a vague topic.** *Example*: "Help me rank for project management software".
* **Combine steps into one request.** *Example:* "Research this keyword, build a brief, and write a draft".
* **Hand off a batch.** *Example:* "Write articles from these 5 briefs". Up to 10 articles or research sessions keep running even if you close the panel or reload, and you can pause, cancel, or resume them. Each finished article reports back in the same conversation with a link.
* **Let it handle the how.** The Agent's job is execution. Yours is direction and review.
* **Ask it what to do next.** If you're ever unsure where to start in Frase, the Agent can give you a grounded recommendation based on your site's data.
* **Use it to build your content plan at scale.** When you ask the Agent to plan content, it works from your organization's existing content strategy.

### Requests to Try

**Examples**

* *"What should I create next?"* The Agent analyzes your site data, content gaps, and opportunities, then gives you a prioritized recommendation.
* *"Audit my site and tell me what to fix first."* It runs the audit, interprets the findings, and surfaces the highest-impact issues in plain language.
* *"Write an article optimized for AI visibility on content marketing strategy."* It researches the topic, builds a brief, writes the draft, and scores it for both SEO and GEO before you open the editor.
* *"Optimize this article for GEO and improve its SEO score."* It analyzes the existing content, identifies specific gaps, and applies improvements directly.

{% hint style="success" %}
If you haven't completed the setup steps yet, that's a good place to start before leaning heavily on the Agent. → *See:* [*Connect Your Data*](/get-started/connect-your-data.md)
{% endhint %}


---

# 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.frase.io/automations/meet-the-frase-agent.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.
