MethodMarketingSEOIntermediate

Do SEO keyword research

A keyword map grouped by topic and intent, prioritised by opportunity, with the page that should rank for each cluster.

This is a practical, copy-paste process for planning a new site or content programme.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md

# 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.

What you need to give the AI

Input	Placeholder	Example
Website and niche	[WEBSITE_AND_NICHE]	B2B HR software
Seed topics	[SEED_TOPICS]	payroll, leave management
Target country and language	[TARGET_COUNTRY_AND_LANGUAGE]	India, English
Keyword data	[KEYWORD_DATA]	attach export from Ahrefs/Semrush/Search Console if you have it

Use it when

Planning a new site or content programme.
Traffic has plateaued.

What you get

Keyword clusters table
Intent labels
Priority score
URL map
First 10 pages to create or update

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

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.

Quality checks built into the prompt

• Never invent search volumes, use provided data or label "estimate/unknown".
• One primary cluster per URL to avoid cannibalisation.
• Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

EvidenceRetail

E-Commerce Share of US Retail

Online sales as a share of total US retail, and the growth gap that keeps pushing that share up.

Open evidence Download context file

EvidenceFinance

UPI vs Visa & Mastercard: India’s Payments Rewiring

Ten years of UPI measured against the US card networks, against cash, and against the merchant-discount-rate question reopened by the Taxation and Other Laws (Amendment) Bill, 2026.

Open evidence Download context file

EvidenceFinance

Six-Economy Macro Baseline

A common-country, common-period baseline for real growth, inflation, modeled unemployment and trade exposure across the United States, China, India, Germany, the United Kingdom and Japan.

Open evidence Download context file

Run next

Methods that chain well after this one.

MarketingWrite an SEO content briefA writer-ready brief: search intent, outline, entities, questions to answer, internal links and on-page specs.MarketingRun a technical SEO auditA prioritised technical audit covering crawlability, indexation, speed, structured data and internationalisation.MarketingOptimise an existing page for SEOA page-level rewrite plan: title, headings, content gaps, internal links, schema and snippet targeting.MarketingOptimise local SEO and Google Business ProfileA local-search plan: Business Profile optimisation, citations, reviews, local pages and posting cadence.

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