> 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/feature-reference/deep-research.md). # Deep Research Turn uncertainty into clarity before you ever open a blank page. {% embed url="" %} Frase Research is how you decide what's worth creating, how it should be structured, and where you actually have a chance to win. It helps you understand what search engines expect, what competitors are doing well, and where opportunities exist that others haven't captured yet. {% hint style="success" %} **Prefer to do this hands-free?** You can run any of these research types — validate a topic, map a cluster, size up competitors, or find competitor gaps — and get a brief back by just asking, from Claude, Cursor, or any MCP client. It's included on every Frase plan. See [**Automate with Claude & MCP**](/automations/automate-with-frase-mcp.md). {% endhint %} ### Why Research Comes First Research helps you answer the right questions *before* you invest time writing. * Is this topic even worth pursuing? * What's already working in this space? * What does Google expect to see here? * Where can my content do something better—or different? Research is necessary to write relevant, valuable, and optimized content. ### The 4 Types of Research in Frase Frase offers four distinct research types. Each one helps you answer a different strategic question before you write.
Build a Brief from a Topic **Use this when you're deciding what to write about.** Topic Research analyzes a keyword or idea at a high level so you can quickly judge demand and competitiveness. It helps you: * Validate ideas before committing * Understand search interest * See related questions and opportunities
Topic Research **Use this when you're devising a larger content plan.** Map subtopics, see what ranks in search, and how ideas cluster together before you choose what to write. It helps you: * Improve topical authority * Optimize programmatic SEO strategically * Visualize [content clusters](/core-workflows/content-clusters.md)
Analyze Competition **Use this when you want to know who you're really up against.** Competitor Analysis compares your brand head-to-head against the competitors you choose—who ranks, how strong they are, and how they frame the topic. It helps you: * See who competes for your audience and where they're strongest * Compare SERP visibility, content depth, and positioning side by side * Spot the openings competitors leave—and pin them straight into your brief {% hint style="info" %} Frase asks for the topic, the competitors to compare ([Brand Hub](/feature-reference/brand-hub.md) suggestions help you fill this in fast), and what you want to learn from the comparison. When it's done, you can jump straight into Find Gaps or generate a brief. {% endhint %}
Find Gaps **Use this when you want to find opportunities you're missing.** Content Gap Research identifies topics and keywords competitors rank for that you don't. It's especially useful for: * Finding high-impact content ideas * Expanding topical coverage * Catching up—or pulling ahead {% hint style="success" %} Many teams start here to prioritize what to create next. {% endhint %}
### **How Research Works** The research experience begins with a question: **what are you actually trying to do?** Build a brief from a topic, explore a topic space, size up your competitors, or find gaps they've missed. Each path is tailored to the goal. Before the research runs, Frase asks four quick questions—topic, goal, audience, and market. This locks in the strategy before the SERP analysis runs, so the keywords, evidence, and brief structure it surfaces are anchored to what this specific piece needs to accomplish—not just what's generically ranking. You can also apply your [Brand Hub](/feature-reference/brand-hub.md) writing settings—brand voice, term rules, reference docs—before a single search query runs. ### **Where Research Fits in the Content Workflow** Research is the first step in Frase's content flow: {% stepper %} {% step %} ### **Research** You research to decide what matters. {% endstep %} {% step %} ### Brief You brief to plan structure and focus. {% endstep %} {% step %} ### Content You write with clarity and intent. {% endstep %} {% endstepper %} ### **How Research Flows Into Briefs** Frase lets you move from research into briefs in two ways: * From **Plan & Create → Research**, you can intentionally **run research first**, then create briefs using what you've learned. * From **Plan & Create → Content** and *+ New Content* button, you can **jump straight into creating a brief** and let Frase research topics and competitors automatically in the background. Either way, every brief is grounded in SERP insights—so writers (and Frase) know what matters before drafting begins. {% hint style="success" %} **The result:** clearer briefs, fewer revisions, and content that starts aligned instead of hoping to get there later. {% endhint %} #### Keep a Brief in Sync With Your Research Research doesn't always stand still after you've built a brief. If you go back and change what the brief is based on—pin new evidence, add keywords, or adjust the plan—Frase marks the brief as stale instead of quietly serving the old version. Open the Research session and you'll see a "**Research updated"** banner with an **Update brief** button. Click it to regenerate the brief from your current research, so the plan reflects what you actually pinned. {% hint style="info" %} A couple of things worth knowing: * If the brief is already current, regenerating does nothing and costs you nothing. * If you've already started the article, or hand-edited the brief, Frase leaves your original untouched and builds a fresh version from the new research instead of overwriting your work. {% endhint %} ### How to Review Research
Summary Tab — Your control room to choose what goes into the brief. You have full control to pin and curate which keywords, SERP structure, AI visibility signals, and supporting evidence integrate into your content brief and article.
SERP Tab — See how competitors have structured their content. Word counts, domain authority, heading hierarchy. Everything you'd expect, informing a smart output.
Keyword Tab — Difficulty, coverage, and intent in one view. Pin the terms you want the brief to target. The bottom bar tracks what you've committed to as you go.
AI Visibility Tab — View AI platform opportunities and competitor gaps. Before you write a word, you can see which AI platforms are citing your competitors and where the gaps are for you to fill. Pin your strongest evidence—stats, quotes, and facts straight into the brief.
When you're ready, the **brief** is a complete strategic document with content type, target tone, core argument, a section-by-section outline with evidence already mapped in, plus a do's and don'ts guide. Everything a writer (whether in-house or AI-driven) needs before they start. Use the **Brief Builder** on the right side-panel to track progress and make adjustments as needed. {% hint style="success" %} **Want to make changes?** Use *Ask AI*. From there, hit Write to generate content, export the brief and write it yourself, or hand it to a freelancer. The brief is yours to use however you normally would. {% endhint %} ### How to Research for Existing Content Keyword, SERP, and competitor research also lives right inside the content editor. The **Keyword** **Research** tab of the right sidebar helps you initiate research, and the **Checklist** tab helps you optimize:
* Every evidence row links to its source, so you can check the claim before you use it. * Draft on a topic row writes that section into your document, dropped in below the most-related section. * As you write, the topics and questions you've covered tick themselves off. {% hint style="info" %} **You can research for** [**imported existing articles**](/core-workflows/optimize-existing-content.md) **too.** If an imported article doesn't have a primary keyword yet, Frase asks for one first, then runs research against it. {% 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 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.frase.io/feature-reference/deep-research.md?ask=&goal= ``` `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.