Black Box: finding yesterday's warning signs in 225,000 maintenance reports
An early-warning system for airframes — two public datasets, one FalkorDB graph, a very stubborn time machine, and an AI agent that isn't allowed to approve anything.
Tag archive
An early-warning system for airframes — two public datasets, one FalkorDB graph, a very stubborn time machine, and an AI agent that isn't allowed to approve anything.

How we built CaseFile, a graph-walking investigation agent, in one hackathon day — and what it taught...
Every company has the same problem: the answer to "why did we deprecate the v1 Auth Service, who...
I am a beginner developer, and for Graph Hacks 2026 I built RippleMind AI: a small tool that answers...
When entity resolution fails, the same company becomes seven different graph nodes. What that looks like in practice, using Samsung Electronics, Samsung SDI, and ASML.

My journey into recommendation systems started with curiosity: how do large companies decide what to...
Building an investing knowledge graph, part 5: what LIVE actually means Part 4 ended with...
Building an investing knowledge graph, part 6: if you're merging data from more than one...
Here is a Cypher query I can now run against the investing knowledge graph: MATCH path =...
Building an investing knowledge graph, part 4: building the resolver Part 3 ended with a...
How to build one recommendation system that can work with different types of items instead of...

The rise of Retrieval-Augmented Generation (RAG) in AI applications has brought forward new...