Cortrix Blog https://cortrix.ai/blog/ Cortrix product updates and practical readings on semantic systems, retrieval, and agent memory. en-us Cortrix RC2: 24.4% higher FiQA recall, with Apache 2.0 https://cortrix.ai/blog/cortrix-rc2-release/ https://cortrix.ai/blog/cortrix-rc2-release/ Cortrix RC2 brings 24.4% higher FiQA Recall@10 in the published comparison, Apache 2.0 licensing, and practical ingestion and agent integration fixes. Scott Product updates Cortrix Handles Retrieval. Jev or Laya Can Help the Agent Decide. https://cortrix.ai/blog/jev-laya-agent-decision/ https://cortrix.ai/blog/jev-laya-agent-decision/ Cortrix retrieves relevant material and preserves its sources. An agent combines that with current business state, then can use Jev or Laya to assess its next step. Scott Inside Cortrix Thu, 24 Sep 2026 00:00:00 GMT Vector is not semantic https://cortrix.ai/blog/vector-is-not-semantic/ https://cortrix.ai/blog/vector-is-not-semantic/ A small retrieval demo separates similarity, ranking, lifecycle checks, and the application rule that decides whether a result is usable. Scott Inside Cortrix Jev and Laya are getting hyped. We're passing for now. https://cortrix.ai/blog/jev-laya-no-go/ https://cortrix.ai/blog/jev-laya-no-go/ Jev can judge a candidate set, but it cannot improve recall. We reviewed the public evidence and decided not to replace Cortrix's local BGE path. Scott Inside Cortrix Mon, 21 Sep 2026 13:31:51 GMT DBpedia explained: why linked data still matters https://cortrix.ai/blog/dbpedia-linked-data-explained/ https://cortrix.ai/blog/dbpedia-linked-data-explained/ Why stable identities and linked data still matter when your agents retrieve knowledge from different systems. Scott Knowledge graphs TransE explained: relationships beyond vector similarity https://cortrix.ai/blog/transe-knowledge-graph-embeddings/ https://cortrix.ai/blog/transe-knowledge-graph-embeddings/ What the simple h + r ≈ t formula tells us about relationships in a knowledge graph, and what a similarity score leaves out. Scott Knowledge graphs RAG explained: external memory brings data governance back https://cortrix.ai/blog/rag-external-memory-data-governance/ https://cortrix.ai/blog/rag-external-memory-data-governance/ RAG lets a model use external knowledge. The original paper also helps explain why sources, updates, and data governance still matter. Scott Retrieval Reflexion explained: agent memory without weight updates https://cortrix.ai/blog/reflexion-agent-memory-without-weight-updates/ https://cortrix.ai/blog/reflexion-agent-memory-without-weight-updates/ Reflexion turns feedback into memory without changing model weights. Its most useful lesson may be about the evaluator. Scott Agent memory HippoRAG explained: why RAG comes back to knowledge graphs https://cortrix.ai/blog/hipporag-knowledge-graphs-for-rag/ https://cortrix.ai/blog/hipporag-knowledge-graphs-for-rag/ HippoRAG connects clues across documents with a knowledge graph. Here is how it works, and where the graph can go wrong. Scott Retrieval