Traditional keyword research: open tool, type seed keyword, scroll through hundreds of results, export CSV, filter in a spreadsheet, repeat. The research and the planning happen in completely different places.
This tutorial does it all in one conversation. Your AI assistant classifies intent, estimates volumes, and maps everything to a content outline. No exports. No tab switching.
We'll use a real example throughout: keyword research for a beginner's guide to making cold brew coffee at home.
The AI Keyword Research Workflow
Eight steps from seed topic to prioritised keyword plan -- all in one conversation
1🌱
Seed Topic
Give Claude your topic and audience context
2🔍
Discover Keywords
Pull real Google Suggest data via SEO
3❓
Question Keywords
Surface what people actually ask
4🎯
Classify Intent
Map keywords by search intent type
5🌿
Expand Variations
Find long-tail opportunities
6📊
Estimate Volume
Prioritise by relative demand
7📝
Map to Content
Build your outline from keyword data
8✅
Priority List
Final ranked keywords with rationale
What you'll have at the end: A prioritised keyword list mapped to a content outline, ready to hand to a writer (or write yourself).
What you'll need
A seed topic. Ours is "cold brew coffee at home," but any topic works.
An AI assistant. ChatGPT, Gemini, or Claude. Every prompt in this tutorial works in any of them.
Google Search Console access (optional). Useful for validating which queries you already rank for. If you don't have Search Console set up yet, run your site through our free SEO analyzer to see where you stand.
Ooty SEO for live data (optional). Pulls real Google Suggest results directly into your AI conversation via MCP.
Two ways to follow this tutorial
Manual approach. Use Google Keyword Planner and Google Suggest to gather raw keyword lists, then paste them into ChatGPT (or whichever assistant you prefer) to classify and map.
Connected approach.Ooty SEO pulls live suggest data through MCP, so your assistant can discover, classify, and map keywords without leaving the conversation. If you haven't set it up yet, see our getting started guide.
This tutorial uses the connected approach, but every prompt works with manual research too.
Every SEO tool on the market will sell you a 400-item audit. Red warnings, orange warnings, yellow warnings. Duplicate meta descriptions on your privacy policy. Missing alt text on a decorative SVG. H2 tags out of order on a page nobody visits. You get a sever
"Running shoes" gets 200,000 searches per month. "Best trail running shoes for wide feet under $100" gets maybe 150. But the person typing that second query is ready to buy. They know the terrain, they know their foot shape, and they know their budget. All the
ChatGPT for SEO strategy means using the model to accelerate the research, analysis, and planning stages of SEO, not to replace the strategic thinking that makes a plan worth executing. You can build a complete quarterly SEO plan in a few hours instead of a fe
Start with context, not just a keyword
The biggest difference between good and mediocre keyword research is context. Don't just type a seed keyword. Tell the AI who you are writing for.
I'm writing a guide for people who want to start making cold brew
coffee at home. They're complete beginners. They've never made cold
brew and probably own basic kitchen equipment, nothing specialised.
Help me find keywords for this guide. Start by discovering what
people actually search for around this topic.
Your AI calls Ooty SEO's keyword discovery tools and returns real Google search suggestions: "cold brew coffee ratio", "how long to steep cold brew", "cold brew coffee maker vs pitcher". These are actual queries people type, not interpolated database entries.
C
Prompt to Claude
“I’m writing a beginner’s guide to cold brew coffee at home. My readers own basic kitchen equipment and have never made cold brew before. Find keywords for this guide -- start by discovering what people actually search for, then expand into question keywords, classify everything by intent, and give me a prioritised list mapped to content sections.”
Questions are high-value targets. They map directly to headers, match voice search, and often trigger featured snippets.
Now find question-based keywords. Things people ask with "how to",
"what is", "why does", "how long", "can you". I want to understand
what beginners are confused about.
You'll get queries like:
"how long to steep cold brew coffee"
"why is my cold brew bitter"
"can you make cold brew with regular coffee"
"how much coffee for cold brew"
These are the exact questions your content should answer.
Classify by intent
Not all keywords want the same content. Someone searching "cold brew coffee ratio" wants a specific answer. Someone searching "best cold brew maker" is comparing products. One page can't serve both well.
Classify the keywords by search intent: informational (learning),
commercial (comparing), transactional (buying), navigational
(looking for a specific brand).
This tells you which keywords belong in your beginner's guide (informational), which need a separate product comparison (commercial/transactional), and which you should skip.
Search Intent Classification
Not all keywords want the same content -- intent determines the right format
Informational
55%
Learning and researching. Examples: how to make cold brew, cold brew ratio
Best content type: Guides, tutorials, explainers
Commercial
22%
Comparing options before buying. Examples: best cold brew maker, french press vs cold brew
Looking for a specific brand. Examples: Starbucks cold brew recipe, Chameleon cold brew
Best content type: Brand pages (low priority for you)
Find long-tail variations
Once you have core keywords, expand into more specific versions. These are lower competition and indicate very precise needs.
Take "cold brew coffee ratio" and expand it. I want specific,
long-tail versions where the searcher has a particular situation.
You'll see things like "cold brew coffee ratio for concentrate", "cold brew coffee ratio tablespoons", "cold brew ratio 32 oz pitcher". Perfect for FAQ sections and subheadings.
Get volume estimates
Before committing, get a sense of relative demand.
Estimate search volumes for the top 15 keywords from our research.
I want to know which ones to prioritise.
A note on accuracy: All volume estimates are directional, not exact. Google's own Keyword Planner groups volumes into ranges. A keyword showing 1,200/month is likely more popular than one at 200/month. Don't treat exact numbers as gospel.
Map keywords to a content outline
This is where the single-conversation approach pays off. No export step. No separate planning doc.
Based on all the keywords we've found, build an outline for my
beginner's guide. Map keywords to the most relevant sections so
I know what to cover and where.
Your AI uses the full research conversation to suggest a structure:
Introduction: cold brew at home, is cold brew easy to make
Equipment: what you need, do you need special coffee
The Ratio: cold brew coffee ratio, tablespoons, concentrate vs regular
The Process: step-by-step how-to, how long to steep
Troubleshooting: why is my cold brew bitter, too weak, too strong
FAQ: can you use regular coffee, how long does cold brew last
Build the final priority list
Give me a prioritised list of 20 keywords for this guide.
Split into: primary keyword (main target), secondary keywords
(important variations), supporting keywords (FAQ and subheadings).
Brief rationale for the prioritisation.
That's a keyword plan with rationale. Something you could hand to a writer with clear instructions.
Time Comparison
Minutes per task: traditional manual tools vs Claude + SEO
Traditional Tools
215min
Claude + SEO
19min
Per-Task Breakdown (minutes)
Seed expansion
25m/2m
Question discovery
30m/2m
Intent classification
45m/3m
Volume estimation
15m/2m
Content mapping
40m/5m
Gap analysis
60m/5m
Tips that matter
Iterate in the same conversation. If the first batch misses the mark, say so. "These are too advanced. I need keywords for people who have never made any specialty coffee." The AI adjusts without starting over.
Don't chase volume blindly. A keyword with 800/month and clear commercial intent is often more valuable than one with 5,000/month and vague informational intent. Intent beats volume.
Separate research by intent. Keep informational keyword research separate from commercial research. They need different content formats. Mixing them creates pages that try to do everything and satisfy nobody.
Volume estimates aren't competition estimates. Google Suggest data shows what people search for. It doesn't tell you whether you can rank. A 10,000/month keyword dominated by major brands isn't easier to rank for just because you found it.
Don't stop at the keyword list. If you end the session without a content plan, the research hasn't delivered its value. The outline step is where research becomes actionable. Our topic cluster mapper can help you visualise how your keywords group into pillar and cluster content.
