# Find the words your category searches with

> See how viewers and creators phrase the problem, then brainstorm keyword angles with that language in hand.

- For: SEO lead
- Category: Sales, Marketing & Brand
- MCP tools: deep_search, chat
- HTML version: https://veridive.com/mcp/use-cases/category-language-brainstorm

## The problem

Keyword research has a chicken-and-egg blind spot: tools report what people already type, which reflects what content already exists. The phrasings your market *speaks* — in questions to creators, in how tutorials title the pain, in the vocabulary of comment sections — run ahead of the typed record. By the time a phrasing shows volume in a keyword tool, someone else owns the SERP.

The spoken layer is the early signal: how people describe the problem before the search engine teaches them the "correct" query. SEO teams that mine it write for phrasings six months before the tools confirm them — which, in content SEO, is the entire game.

## How veridive MCP helps

**deep_search** reads the spoken layer: how creators title and phrase the problem space, what vocabulary the how-to content in your category actually uses, which question-formulations recur. Transcript-level search means you're mining real usage, not guessing at it.

**chat** turns the mined language into keyword strategy — the no-retrieval half of the workflow: cluster the phrasings, generate long-tail variants, map them against your existing coverage. The brainstorm runs grounded in observed language instead of starting from your team's internal jargon — which is where most keyword lists quietly go wrong on day one.

## How to run it

1. **Connect veridive MCP** — One-time setup: add the veridive MCP server to Claude, ChatGPT, Cursor or any MCP client and generate your API key. Takes about two minutes.
2. **Mine the spoken phrasings** — How the category's creators and audiences actually phrase the problem — the pre-typed layer.

   ```
   How do creators and viewers in the <category> space phrase the core problems — the recurring question formulations and pain vocabulary? Use veridive's deep_search.
   ```
3. **Cluster and expand** — The brainstorm, grounded: cluster the observed language, generate variants, spot the gaps.

   ```
   Cluster these phrasings by intent, expand each cluster with long-tail variants, and flag which clusters our current content doesn't cover.
   ```
4. **Prioritize by earliness** — The phrasings spoken often but typed rarely are your six-month head start.

   ```
   Which of these phrasings look common in speech but underserved in written content? Those are the early-mover targets — rank them.
   ```

## Problems it solves

- Keyword tools report the past — phrasings that already have owners.
- Keyword lists start from internal jargon and drift from how buyers actually talk.
- The spoken-language early signal exists but has never been minable at scale.
- Content calendars chase confirmed volume into the most crowded SERPs.

## Why it's valuable

- Six months of lead on phrasings the tools haven't confirmed yet.
- The brainstorm starts from observed language — grounded, not guessed.
- Speech-common/type-rare gaps are ranked explicitly: the early-mover list.
- Pairs with the voice-of-customer file: one mining pass feeds SEO and copy both.

## Example prompts

```
How do <category> creators and viewers phrase the core problems? Recurring formulations — use veridive's deep_search.
```

```
Cluster by intent, expand long-tails, flag our coverage gaps.
```

```
Rank the speech-common but content-underserved phrasings.
```

## FAQ

**Does this replace my keyword tool?**

No — it front-runs it. The tools confirm and quantify; this finds the phrasings worth checking before they show volume. Use both ends of the pipeline.

**What's chat doing in this workflow?**

The synthesis half: clustering, variant generation and gap-mapping over the mined language — conversational work with no retrieval needed. Facts from the search, strategy from the chat.

**How does this interact with AI-assistant search (GEO)?**

Strongly — assistants answer from natural phrasings, not keyword-ese. Content written in the spoken layer's language tends to be what they cite, which is increasingly its own channel.

## Related use cases

- [Steal your customer's exact words](https://veridive.com/mcp/use-cases/voice-of-customer-phrasing.md) — Mine how real users describe the problem in reviews and vlogs — copy that converts is usually a transcript quote.
- [Find the gaps your niche hasn't covered](https://veridive.com/mcp/use-cases/content-gap-finder.md) — Ask what questions keep coming up with weak answers; the uncovered intersection is your content calendar.
- [Study which webinar formats actually convert](https://veridive.com/mcp/use-cases/webinar-format-analysis.md) — Compare formats across your industry's public webinars and get a cited read on what holds attention.

---

Part of the veridive MCP use-case library: https://veridive.com/mcp/use-cases.md
Server docs for agents: https://veridive.com/mcp.md