Notes on SEO monitoring, AI SEO performance, and how to keep tabs on your brand.
Grounding is when an AI engine answers from live web results instead of training memory. We measured it across six engines on ~2,500 prompts each. Five ground 91–98% of the time, and one, Gemini, grounds just 41%.
The same keyword ranks differently in every city. Here is how much local rankings vary by geography, why the map pack changes week to week, and how to check Google Maps rankings programmatically across a city grid.
If your LangChain or LangGraph agent searches the web, it's probably searching with Tavily, not Google. So how close is Tavily to Google? We put the same 500 queries through both. It's the closest of any search API we've measured, but it reranks Google's sources into an order of its own.
Adverse media screening is the AML control of checking counterparties against negative news. Here's the definition, the pipeline, the tools compared, and a build recipe.
Reputation no longer lives only in reviews and headlines. It's what ChatGPT, Perplexity, and AI Overviews say about you, and no incumbent stack watches that layer.
Exa searches the web by meaning, not keywords. So how different is it from Google, really? We ran 500 identical queries through Exa and cloro's live Google SERP. The overlap is the lowest of any search API we've measured, and that's exactly the point.
cloro read 60 live SERPs: AI Overviews hit 100% of B2B/SaaS queries vs 10% of B2C. How to do B2B keyword research with SERP signals, not unreliable volume.
International keyword research, tested: we scraped one seed across 10 country SERPs and found ~17% overlap. Why translation fails and how to localize instead.
There are three different "Perplexity webs": the Search API, the answer users see, and Google. Most people conflate them. We ran 500 identical queries through the Perplexity Search API and cloro's live Google SERP to measure exactly how far apart they sit.
