Inside Cortrix
Vector is not semantic
A small retrieval demo separates similarity, ranking, lifecycle checks, and the application rule that decides whether a result is usable.
Writing
Notes with enough context to remain useful.
A selected record of writing published with Cortrix, preserved here with its original context and sources.
Knowledge graphs
DBpedia explained: why linked data still matters
Why stable identities and linked data still matter when your agents retrieve knowledge from different systems.
Knowledge graphs
TransE explained: relationships beyond vector similarity
What the simple h + r ≈ t formula tells us about relationships in a knowledge graph, and what a similarity score leaves out.
Retrieval
RAG explained: external memory brings data governance back
RAG lets a model use external knowledge. The original paper also helps explain why sources, updates, and data governance still matter.
Agent memory
Reflexion explained: agent memory without weight updates
Reflexion turns feedback into memory without changing model weights. Its most useful lesson may be about the evaluator.
Retrieval
HippoRAG explained: why RAG comes back to knowledge graphs
HippoRAG connects clues across documents with a knowledge graph. Here is how it works, and where the graph can go wrong.
Product updates
Cortrix RC2: 24.4% higher FiQA recall, with Apache 2.0
Cortrix RC2 brings 24.4% higher FiQA Recall@10 in the published comparison, Apache 2.0 licensing, and practical ingestion and agent integration fixes.