Under the hood
How we build a name checker that looks at domains, social handles and what AI models already believe about your brand.
namingdomainsbrand-names
Should You Check Your Name Against ChatGPT?
The short answer is yes, with one correction. ChatGPT alone is not enough, because different AI models know very different things about the same name. How different? We ran the numbers to find out.
Victor Ohachor · Read
seogeoaeo
On-Page Signals That AI Crawlers Look For
But there is a fourth crow, and it beats the other three. Google’s guide says that creating content people find unique, compelling and useful will likely shape your presence in AI search more than anything else in the guide (Google, 2026b). It separates commodity content, the kind that could have come from anyone (its example is “7 Tips for First-Time Homebuyers”), from non-commodity content that carries a first-hand experience nobody else has (Google, 2026b).
Victor Ohachor · Read
namingai-systemdomains
Why Name Generators All Sound the Same (We Fixed Ours)
The trouble is that the cure became the disease. Strip out every dictionary word, every compound, every recognizable suffix, and what is left? Invented five-to-ten-letter strings. Run the pipeline on a lawyer tool or a dog food brand and you get Veltrix, Moxen, and Pultra for both. The lists were available but characterless, and a characterless list is indistinguishable from every other generator on the planet (errrhh... I meant Internet).
Victor Ohachor · Read
bug-fixesdebuggingnextjs
Our App Just Wouldn't Let Go
The solution was to delete the cookie from within the server action. Whenever cookies() is modified within a server action, Next itself emit the deletion Set-Cookie on the action's response, which the browser will definitely receive this time.
Victor Ohachor · Read
raghydequery-rewriting
Retrieval Semantics: HyDE vs Query Rewriting
Any RAG system is built to prevent hallucination by providing additional context beyond just what the model has learned in its training dataset. Doing it means retrieving this context reliably, including it in the prompt, and passing it to the model. As simple as that sounds, retrieving context reliably is a hard task and tackling it poorly introduces a problem that can condemn any RAG system to an execution by hanging (plus the creative profanity that anyone who has ever been stuck in that system will most likely utter).
Victor Ohachor · Read
