Content related to Three Things You can do Today to Get the Most out of Microsoft 365’s Project Cortex
Knowledge Cast – Bridging Knowledge, Data, and AI by Zach Wahl, Joe Hilger, and Lulit Tesfaye
In this special episode of Knowledge Cast, Zach, Joe, and Lulit pass the mic to Senzing‘s Paco Nathan, who interviews them about their new book Bridging Knowledge, Data, and AI: Harnessing the Semantic Layer Framework to Drive Intelligence. Paco guides … Continue reading
Knowledge Cast – Lasse Andresen, Founder & CEO of IndyKite
Enterprise Knowledge COO Joe Hilger speaks with Lasse Andresen, founder and CEO of IndyKite Inc., the first system of intelligence built on a live context graph. The result is agentic AI that can operate across platforms with precision and deliver … Continue reading
What is the Difference Between a Semantic Layer and a Context Layer? When to Use a Knowledge Graph vs. a Context Graph
Before AI became part of everyday conversations, most enterprise knowledge and data projects had a somewhat straightforward goal: to create a “single source of truth.” In theory, this meant that everyone in the company could look at the same search … Continue reading
Leveraging a Semantic Layer for Research Curation and Conversational Experiences
The Challenge A global philanthropic organization focused on health programs struggled to fully leverage knowledge from semi-structured and unstructured documents. Specifically, within a health-related funding program, researchers lacked access to key qualitative data from end-user surveys and transcripts. Consequently, they … Continue reading
Building the Semantic Layer: Scaling Enterprise Intelligence at a Global Investment Firm
The Challenge A global investment firm with a $330 billion dollar portfolio and 50,000+ employees struggled with fragmented data. Investment professionals were losing critical time hunting for assets across disconnected systems. Detailed deal records were scattered as a mix of … Continue reading
GraphRAG in the Enterprise
Retrieval-Augmented Generation (RAG) is a commonly utilized pattern for grounding large language models in enterprise data. Instead of solely relying on a model’s training, RAG collects relevant information from internal sources, documents, knowledge bases, and other systems; it then uses … Continue reading
Optimizing Historical Knowledge Retrieval: Extracting Knowledge by Making Connections
The Challenge From POC to Production A Federally Funded Research and Development Center (FFRDC) faced significant challenges with low-quality or incomplete metadata for managing and cataloging scientific reports, hindering researchers’ ability to parse repositories and efficiently discover relevant content. As … Continue reading
What Are Explainable AI Knowledge Portals and Why Do You Need Them?
Knowledge Portals first came into prominence in the early 2000s. These initial portals were a collection of static links to information on everything from HR systems to company policies and communications. It was a single location to access the systems … Continue reading
Graph Database Evaluation for a Financial Services Firm
A financial services firm built a mature graph data ecosystem, but the graph database they selected originally did not scale as multiple business-critical solutions relied on graph data. As application and business teams across multiple stakeholder groups expanded usage … Continue reading
Taxonomy Alignment for SDG Tagging
In the session “Utilizing Taxonomies to Meet UN SDG Obligations“ co-presented at KMWorld 2025 on November 17th, Enterprise Knowledge’s Ben Kass and ASHA’s Mike Cannon discuss how they structured taxonomies within an ongoing auto-tagging implementation to serve content management and … Continue reading