Knowledge graph for AI agents: what it takes to run one in production
What a knowledge graph for AI agents costs to run: ownership, maintenance, lakehouse fit, and where graphs earn their cost. A production operating guide.
Learn from experienced data practitioners
Data engineering, knowledge discovery, semantic AI, and more.
All
Knowledge Graphs and Semantics
Enterprise Data Strategy
AI and GenAI
Industry Use Cases
Search, NLP and Text Analytics
Data Governance and Quality
Data management
marklogic
Company Insights and Announcements
Data Architecture and Platforms
GraphRAG
Data intelligence
Events and Community
Trust Signals
AI and LLMs
FAIR
News and events
Agentic AI use cases in regulated industries
Six agentic AI use cases in regulated industries, scored by autonomy, evidence, and data prerequisites, plus how to sequence your first deployment.
%20Why%20AI%20agents%20dont%20just%20need%20data.png?length=700&name=Hero%20image(%20dark)%20Why%20AI%20agents%20dont%20just%20need%20data.png)
AI agents don’t just need data. They need a company brain.
AI agents need more than data. Discover how semantic context, knowledge graphs, and governed knowledge build a trusted foundation for enterprise AI.
by
Clive Smith
The real cost of delaying FAIR data principles in life sciences
Delaying FAIR data principles in life sciences can slow AI features, data reuse, and product delivery. See the evidence and when waiting is defensible.
How publishers can add integrity screening without disrupting editorial workflows
Integrity screening should fit editorial workflows, connect data, and reduce technical burden across digital publishing platforms.
by
Elaine Ellerton
Data readiness for AI: why most enterprises aren't AI-ready yet
Data readiness for AI requires more than data quality and governance. Learn why semantic readiness is the missing layer for production-grade enterprise AI.
AI Data Governance: Foundation for an AI-First Enterprise
AI data governance turns a data estate into a foundation an AI-first enterprise can operate on. See the three architectural foundations that make it work.
Why trust, not model capability, will define enterprise AI success
Discover why trusted enterprise AI depends on governance, semantic context, explainability, and connected knowledge, not model capability alone.
by
Avinash Dixit
From data governance to decision governance in enterprise AI
Learn how decision governance extends data governance for AI-driven decisions, with traceability, policy alignment, human review and audit-ready outputs.