Write an SEO content brief
A writer-ready brief: search intent, outline, entities, questions to answer, internal links and on-page specs.
This is a practical, copy-paste process for commissioning a writer or an ai to write a ranking article.. 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].
# Write an SEO content brief Method by Deepstory Research: deepstoryresearch.com/method/seo-content-brief You are an SEO content lead. Follow the method below step by step. Goal: A writer-ready brief: search intent, outline, entities, questions to answer, internal links and on-page specs. ## My inputs - Target keyword: [TARGET_KEYWORD] (example: how to calculate gratuity in UAE) - Audience: [AUDIENCE] (example: HR managers and employees) - Top-ranking pages: [TOP_RANKING_PAGES] (example: paste 3 URLs or summaries) - Your site’s angle or expertise: [YOUR_SITE_S_ANGLE_OR_EXPERTISE] (example: payroll software provider) 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. Describe the search intent and what the searcher needs to leave satisfied. 2. Analyse what top results cover and where they are weak. 3. Draft an H1–H3 outline. 4. List entities, terms, and questions (People Also Ask style) to cover. 5. Specify title tag, meta description, URL, schema and internal links. 6. State the information gain: what we add that others do not. ## Deliver the output in this structure - Intent summary - Competitor gaps - Outline - Entities & questions - On-page specs - Information-gain angle - Word-count range ## Quality rules - Title ≤60 chars, meta ≤155 chars, count them. - Include a factual-accuracy checklist for any law, rate or number. - 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 |
|---|---|---|
| Target keyword | [TARGET_KEYWORD] | how to calculate gratuity in UAE |
| Audience | [AUDIENCE] | HR managers and employees |
| Top-ranking pages | [TOP_RANKING_PAGES] | paste 3 URLs or summaries |
| Your site’s angle or expertise | [YOUR_SITE_S_ANGLE_OR_EXPERTISE] | payroll software provider |
Use it when
- Commissioning a writer or an AI to write a ranking article.
What you get
- Intent summary
- Competitor gaps
- Outline
- Entities & questions
- On-page specs
- Information-gain angle
- Word-count range
The procedure, step by step
Read this before you run it, so you can check the AI actually followed the method.
Describe the search intent and what the searcher needs to leave satisfied.
Analyse what top results cover and where they are weak.
Draft an H1–H3 outline.
List entities, terms, and questions (People Also Ask style) to cover.
Specify title tag, meta description, URL, schema and internal links.
State the information gain: what we add that others do not.
Quality checks built into the prompt
- • Title ≤60 chars, meta ≤155 chars, count them.
- • Include a factual-accuracy checklist for any law, rate or number.
- • 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.
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.
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.
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.
Run next
Methods that chain well after this one.
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.