AI Briefing#knowledge-graph
The latest AI and developer news about #knowledge-graph, with the original source and a short summary.
The latest AI and developer news about #knowledge-graph, with the original source and a short summary.
Eugene Group conducted a PoC to convert building materials distribution data into a knowledge graph using Amazon Neptune and Bedrock, validating the effectiveness of seven business CQs.
Adding an evidence graph to the OpenWiki memory layer improved accuracy by 27% and cut cost per correct answer by 58%.
A prototype system processed 45,047 Enron emails to create a 214-page entity wiki where 93% of sampled facts were verified as fully supported by source documents.
The platform uses a dynamic knowledge graph and agentic AI to correlate infrastructure and workload telemetry, helping operators trace issues across hundreds of thousands of GPUs.
Netflix's new Observability Ontology standardizes entity definitions across tools like Atlas and Radar, absorbing the manual context-assembly phase of investigations that previously took hours.
Musinsa improved CTR by 21.3% by applying knowledge graph-based unified embeddings to personalized push notifications.
Toss Securities introduces the process of advancing its recommendation and search systems toward real-time personalization and RAG-based architectures.
We validated a method for sharing domain knowledge among AI agents using a two-layer semantic layer composed of a standards-based Core and an organization-specific Overlay.
Yeogi-eottae Company designed a data pipeline to build an Agentic RAG MCP that leverages internal knowledge.
DeepAmbigQA combines ambiguity and multi-hop reasoning to evaluate the answer completeness of LLMs.
Marble has released 1,590 elementary learning concepts as a prerequisite relationship graph.
Toss built a 'Topic' system that connects documents, code, and messenger conversations so LLMs can accurately understand internal company information, managing trustworthy context.
It introduces GBrain, a knowledge layer that helps AI agents manage personal knowledge and generate citation-based answers.
An open-source project has been released that uses a local LLM to extract relationships between concepts from text and build a knowledge graph.
Microsoft has released 'Ontology Playground,' an open-source web application that supports ontology design and learning.
This covers a strategy for managing domain knowledge as a graph-structured asset so that AI doesn't create duplicate features.
graphify, a tool for AI coding assistants that maps code and documentation into a knowledge graph so developers can explore via questions instead of file search, has been released.
A new graphdb has been released that can handle large-scale graph data while minimizing memory usage.
As we prepare for the era of Agentic AI, which goes beyond simple text generation to carry out goals, securing observability through ontology is key.
LG AI Research showcased structural reasoning technology combining knowledge graphs and LLMs at AAAI 2026, demonstrating agent reliability and efficiency.
It's a local-first AI agent that indexes your work history into a knowledge graph to provide personalized AI workflows.
A new knowledge graph structure is proposed that treats relationships (Edges) as independent embedded documents rather than simple metadata.
MOTHRAG, a framework that reduces data update costs through query-time orchestration without graph construction, has been released.
POSCO DX defined senior engineers' experiential tacit knowledge as UDK that AI has not learned, and verified a method to structure it into a knowledge graph to implement design automation.