Retrieval Architecture
Check if ChatGPT and Perplexity can actually read your site
What it does
Retrieval Architecture is a technical GEO/AEO consultancy. Audit website architectures for RAG systems, passage retrieval, and Wikidata entities.
When ChatGPT, Perplexity, or Gemini answer a question about your product, they cite you or a competitor. I find the technical reasons your site gets skipped, how it renders, how it's structured, how your brand is identified, and fix them. AI engines don't rank pages by keywords anymore. They break your site into chunks, match those chunks by meaning, and check whether your brand is a recognized, disambiguated entity. Here's what that looks like in practice. Retrieval-Augmented Generation systems break documents into blocks. Clean DOM elements determine the quality of the generated vector embeddings. AI models associate product names and brands with standard knowledge databases (such as…from retrieval-architecture.vercel.app
Does the same job
all alternatives →
AIO.GEO Protocol24d ago · aiogeoprotocol.com · ▲79Audit AI search structure. Dry run fixes. Receipts.
More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com