Keyword research is one of those SEO disciplines that looks mechanical from the outside but is actually driven by judgement calls at every step. AI tools — ChatGPT specifically — have changed which parts of that process are worth automating and which parts still need a human eye. This is the framework shared at SEO Vibes Tour Athens by our SEO team: a practical three-step workflow that uses ChatGPT where it genuinely multiplies time efficiency, without handing over the judgement calls that should stay human.
Step 1 — Intelligent keyword research organisation
Before any AI involvement, the research plan needs structure. A typical e-commerce or B2B site has dozens of intent clusters — buying intent, informational intent, comparative intent, branded versus non-branded, long-tail variants by persona. Without that structure, AI-generated output produces volume but no coherence.
The work at this step is human: define the clusters you are researching around, map the customer journey stages the keywords should support, and set the boundaries of what is in scope versus what is a different project. AI can help draft cluster hypotheses, but the final cluster architecture is a judgement call.
Step 2 — Use ChatGPT to automate and optimise the process
Once the cluster architecture is set, ChatGPT becomes genuinely useful as a volume generator. The pattern we use:
- Expand seed keywords into long-tail variants across each cluster, orders of magnitude faster than manual brainstorming
- Infer search intent per keyword by prompting for the underlying question a user is likely asking
- Generate topical outlines for cluster-level content briefs, which the SEO team then reviews and refines
- Cross-check competitor coverage — prompt the model with competitor URLs and ask what keyword gaps are visible
Critically, none of this output ships as-is. It is raw material for the SEO team to validate with classic tools (Search Console, keyword volume data, SERP inspection) and with their own judgement.
Step 3 — Iterate based on real results
The third step is where most AI-assisted keyword workflows break down. Teams prompt, get output, ship, and never close the loop. The discipline is to feed real performance data back into the prompting workflow — which keyword clusters actually drove traffic, which content briefs converted, which terms the AI over- or under-indexed on.
After a few iteration cycles, the prompting gets sharper, the output gets more aligned with what actually works in this specific site and vertical, and the time saved compounds. The key to success is maximising time efficiency and human productivity — not replacing the SEO practitioner, but removing the tedious volume work so the practitioner can spend time on the judgement calls that matter.