An independent AI research lab
Studying how AI systems find, read, and cite the web.
Prodius Enterprise is the personal lab of Cristian Frunze. I run experiments on LLM retrieval, AI crawlers, and generative engine optimization — and publish everything I learn, including what didn't work.
Research areas
Four questions, studied in the open.
LLM retrieval & citation
How assistants pick their sources: what gets retrieved, what gets cited, and how that differs across models and question types.
AI crawlers & indexing
What GPTBot, ClaudeBot, PerplexityBot and friends actually fetch, how they respect (or ignore) directives, and how crawling translates into visibility.
Generative engine optimization
Separating measured effect from cargo-cult advice: which on-page changes demonstrably shift inclusion in AI answers.
Retrieval quality & evaluation
The engineering side: embeddings, chunking, and ranking — and small, honest, reproducible benchmarks for judging them.
Have a question the lab should look at?
I take a small amount of advisory and collaboration work, and I'm always interested in good research questions.