---
type: method
slug: seo-keyword-research
title: "Do SEO keyword research"
category: "Marketing"
subcategory: "SEO"
level: intermediate
source: https://deepstoryresearch.com/method/seo-keyword-research
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Planning a new site or content programme.
- Traffic has plateaued.

## Prompt

# Do SEO keyword research
Method by Deepstory Research: deepstoryresearch.com/method/seo-keyword-research

You are a technical SEO strategist. Follow the method below step by step. Goal: A keyword map grouped by topic and intent, prioritised by opportunity, with the page that should rank for each cluster.

## My inputs
- Website and niche: [WEBSITE_AND_NICHE]  (example: B2B HR software)
- Seed topics: [SEED_TOPICS]  (example: payroll, leave management)
- Target country and language: [TARGET_COUNTRY_AND_LANGUAGE]  (example: India, English)
- Keyword data: [KEYWORD_DATA]  (example: attach export from Ahrefs/Semrush/Search Console if you have it)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Expand seeds into related terms, questions and modifiers.
2. Classify intent (informational, commercial, transactional, navigational).
3. Cluster keywords that one page can rank for.
4. Prioritise by demand, difficulty, business value (use attached data; otherwise mark volumes as unknown).
5. Map each cluster to an existing or new URL.

## Deliver the output in this structure
- Keyword clusters table
- Intent labels
- Priority score
- URL map
- First 10 pages to create or update

## Quality rules
- Never invent search volumes, use provided data or label "estimate/unknown".
- One primary cluster per URL to avoid cannibalisation.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

## Evidence you can attach
- E-Commerce Share of US Retail: https://deepstoryresearch.com/data/us-ecommerce-share (AI context file: https://deepstoryresearch.com/context/us-ecommerce-share.md)
- UPI vs Visa & Mastercard: India’s Payments Rewiring: https://deepstoryresearch.com/data/upi-vs-cards (AI context file: https://deepstoryresearch.com/context/upi-vs-cards.md)
- Six-Economy Macro Baseline: https://deepstoryresearch.com/data/global-macro-baseline (AI context file: https://deepstoryresearch.com/context/global-macro-baseline.md)

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.