Search for a command to run...
Series
A public engineering journey exploring AI-native knowledge infrastructure. From Knowledge Objects and agent memory to provenance, multimodal ingestion, Rust architecture, storage systems, and real-world benchmarking.
Artificial intelligence is changing the way we build software. We now have AI agents that can reason, use tools, generate code, search for information, and interact with applications. But as AI capabi
In my previous post, I introduced the question behind AIKOQL: What should data infrastructure look like when AI agents become first-class users of that infrastructure? That question naturally leads
In the first two posts of this series, I introduced why I started building AIKOQL and the idea behind the Knowledge Object. But there is an obvious question that follows. Why do we need another abstr
In the previous posts, I introduced why I started building AIKOQL, what a Knowledge Object is, and where I believe AIKOQL fits alongside relational databases, document stores, vector databases, and gr
In the previous posts, I explored why I am building AIKOQL, the idea of Knowledge Objects, where AIKOQL fits in the modern data ecosystem, and how information might move from documents into structured
In most software systems, we think about data as something that changes. A database record is inserted. Then it is updated. Eventually, it may be deleted. But knowledge behaves differently. A piece of
