Applied LLM Research

The Next Economy Runs on Agents. Your Site Is the Infrastructure.

Minnesota.AI is a field lab for AI discoverability engineering. We run controlled experiments on how AI systems find, parse, cite, and route users to websites — and publish the data openly.

Read All Articles View Live Data

Live AI Data Feed

Rolling 24-hour window of AI crawler activity across sites we operate and experiment on. Updated hourly from Cloudflare analytics.

Loading data…

View full feed →

AI discoverability engineering. A new discipline.

What can AI access? — LLM Structure. The semantic markup, entity clarity, and machine-readable patterns that make a site legible to language models.

What does AI understand? — LLM Visibility. The measurable signals that determine whether a model correctly represents what you do.

What does AI choose? — LLM Discoverability. How organizations get cited, recommended, and routed to in AI-assisted search and agent workflows.

01
LLM Structure

The semantic markup, entity clarity, and machine-readable content patterns that determine whether AI systems can parse a site accurately. We study what makes content legible to language models.

02
LLM Visibility

The measurable signals that determine whether a language model understands what an organization does. We research how AI models interpret and represent entities — and what structural patterns drive accurate representation.

03
LLM Discoverability

Visibility is being readable. Discoverability is being chosen. We study how organizations appear in AI-assisted search, answer engines, and agent-driven workflows — and what moves the needle.

04
Applied AI Systems

How lightweight, production-ready systems combine user input, AI inference, decision logic, and measurable outputs. We study what makes these systems work and publish the frameworks behind them.

When language models understand you, they recommend you.

Search behavior is changing. Users are increasingly asking AI systems to compare options, recommend vendors, and guide decisions. Organizations that structure their content for LLMs gain visibility. Those that make their information clear and retrievable gain discoverability.

This is what we study — and everything we find, we publish.

David Valencia, Founder of Minnesota.AI

David Valencia

Minnesota.AI is where I publish what I find about how AI systems discover, interpret, and recommend websites.

More about Minnesota.AI →

Pilots + Partnerships

If you are running a site where AI discoverability matters and want to collaborate on a controlled pilot, we would welcome the conversation.

Get in Touch