Understanding GEO
How generative AIs really decide who to cite, recommend and mention.
20 lessons
- 01
The search landscape in 2026
In 2026, finding information runs through AI summaries and chatbots almost as often as classic links. A tour of the channels and how they balance out.
- 02
Plain LLM vs. retrieval-augmented LLM (RAG)
A plain LLM answers from what it learned during training. A RAG-based LLM fetches up-to-date information before answering. The difference changes everything for your visibility.
- 03
How a RAG-based LLM builds an answer
Query, document retrieval, selection, synthesis, citation: the five concrete steps a chatbot uses to build an answer from the web.
- 04
Fan-out queries: the key concept
A single question asked to an AI often splits into several sub-queries sent in parallel. Understanding this mechanism changes how you should cover a topic.
- 05
How the LLM merges results (reranking)
After retrieving dozens of passages, an AI system has to decide which ones to keep. This sorting step, called reranking, largely decides who gets cited.
- 06
Chunking: how the LLM splits up your content
Before an AI reads your article, it gets split into small, independent blocks. Understanding this splitting process, called chunking, changes how you should write each section.
- 07
Why AIs sometimes ignore your site
Blocked crawlers, generic content, lack of evidence, a brand barely mentioned elsewhere: the most common causes of invisibility in AI answers.
- 08
SEO vs. GEO: the key differences
SEO ranks links, GEO selects cited passages. Two different logics, two different metrics, but a common foundation you shouldn't abandon.
- 09
What makes content "GEO-ready"?
GEO-ready content answers directly within the first sentences, is clearly structured, rests on evidence, and stays understandable section by section.
- 10
Structuring an article for GEO
A short opening answer, self-contained thematic sections, an FAQ, an actionable conclusion: the template for an article designed to be read by generative AI.
- 11
The Q&A / FAQ format and GEO
The Q&A format mirrors how people query generative AI. How to use it to get cited, without falling into hollow, repetitive FAQ blocks.
- 12
Citations, numbers and evidence: why they matter
Generative AI favors content that backs its claims with verifiable data. How to include numbers and citable sources without ever inventing them.
- 13
E-E-A-T: experience, expertise, authority, trust
Google's E-E-A-T framework applies to generative AI too, which looks for reliable sources to cite. How to apply it concretely to your content.
- 14
Prompts and AI queries: how users actually ask
Informational, comparative, transactional: AI queries fall into a few broad families. What each one implies for the content you need to produce.
- 15
ChatGPT, Perplexity, Gemini, Claude: how each picks its sources
Perplexity, ChatGPT, Gemini, Claude: each AI engine has different sourcing habits shaped by its architecture. A careful overview, without overreaching generalizations.
- 16
The goal: being everywhere (AI share of voice)
In GEO, repeated presence on third-party sources matters as much as your own site. Understanding and pursuing your AI share of voice.
- 17
Brand mentions: the #1 factor in AI visibility
Being cited on third-party sites, even without a link, weighs heavily in your odds of being mentioned by an AI. How to generate useful brand mentions.
- 18
Google AI Overviews: the largest AI channel by volume
AI Overviews reach far more searches than all dedicated chatbots combined. What they are and how to improve your odds of appearing in them.
- 19
GEO numbers: market size, ROI and conversion
The GEO market is too young for any single figure to reliably capture its size or ROI. Cautious trends, not invented statistics.
- 20
What academic research says about GEO
The founding paper on Generative Engine Optimization offers a testing methodology, not a magic formula. What it shows, and its limits.