The v2 engine is a new predictive database that holds facts, text, vectors, and relationships in one store and answers calibrated, explainable queries about the unknown. It is in public beta, running alongside v1. This post is concrete on purpose: here is what it does, here are queries you can run, and here are the numbers, including the ones that do not flatter us.

The efficient market hypothesis says you cannot beat the market. Graham, Buffett, and a lineage of growth investors spent decades saying otherwise. So I ran the experiment: grade 250 S&P 500 companies on value, quality, and growth signals, point-in-time, and let a predictive database score all three philosophies against twelve years of real outcomes. The answer surprised the value investor who built it.

Databases are absorbing AI capabilities. A taxonomy of the four categories emerging in 2026: vector databases, ML-in-database platforms, LLM-augmented databases, and predictive databases.