I compared, a google brand search of a person, in Google, Google AI Mode, and then Gemni... I was trying to prove to a "potential client" that I wasn't full of crap and Google was rebuilding its knowledge graph for the new AI world... and he wasn't in it! LOL. Heres a few thoughts Gemni gave me (FYI: this will be a lot to read ) [ prompt for Gemni: I did a search for elizabeth lyons , google does not have a knowledge panel, google shows multiple people, google ai mode shows others and you gemni shows less - is this a relevant observatoin of google redoing its knowledge graph, and moving beyond what was indexed and used for the LLM in the past. ] ///. first reply [System LayerObservation in PracticeExplanation of Phenomenon1. Classic Search Index"Shows multiple people," "no knowledge panel."This is the result of an Entity Disambiguation challenge. When a common name has multiple distinct, globally relevant people (e.g., an author, an academic, a politician), the classic search algorithm recognizes that multiple entities exist but cannot confidently resolve the query to a single, canonical one. Without that high-confidence resolution, the system often defaults to showing the "messy" organic results, and an authoritative, single Knowledge Panel is suppressed.2. Google AI Mode (AI Overviews)"Shows others."AI Mode (powered by customized Gemini models) uses Retrieval-Augmented Generation (RAG). It performs a deeper, semantic search (a "query fan-out") across subtopics and data sources, including the web and the Knowledge Graph. It then synthesizes an answer. Since it is designed for exploratory and complex questions, it might surface a different "Elizabeth Lyons" that the AI model deems most relevant to its synthesized overview, potentially drawing from high-authority sources that the classic panel failed to consolidate.3. Gemini (The LLM)"Shows less."As a large language model, Gemini's responses are often driven by a highly selective and curated knowledge base to ensure factual precision. For entities with common names, the model tends to gravitate toward the one or two most authoritative or well-referenced entities it has high confidence in. By focusing on selectivity over breadth, it appears to "show less" than the raw, noisy index of the classic search results.] [ next reply That is an extremely relevant observation and it beautifully captures the current state of flux in Google's search technology, confirming your hypothesis about the evolution of its knowledge systems.

I tried looking in my email for certification message but did not find. How else can I find?

I've been invited as a guest speaker in the AIEDGE Digital Summit that is taking place from the 18th to the 20th. I'd be talking about AEO from 12:30 Central So our scheduled call might be moved 15 -20 minutes after the scheduled time to 2:15 EST to allow for livestream setup! You're all invited to Join - It's FREE! https://aiedgesummit.com/

Something I’ve been noticing, I’ll ask the same queries across ChatGPT, Perplexity, and Gemini and they all give different answers. Sometimes slightly different, sometimes completely different. And it makes me wonder If even the AI tools can’t agree, how do we know which one is actually “right”? Is it pulling from different sources? Different recency windows? Different confidence levels? I’m genuinely curious if anyone here has figured out how to explain these variations, because I’m still trying to wrap my head around it.

Just so y'all know, the book is not the end of the road... It's the starting point! The discussion is still ongoing and is only getting better. Join Kasim and me as we dabble in what's on the horizon of AI: Google hoarding traffic, AI black boxes, the Agentic web, and AEO as a wide-net strategy—not only to funnel traffic to your offers but to conquer the new frontier of discovery:: Influence the super-intelligence Get recommended by AI, and win the future: Today.